Do files aer_112_9

	1	`*** this script creates caliper tables using our adjustment procedure using different significant thresholds (Tables 2, A5 and A6 in our comment)`
	2
▼	3	`clear` `. clear .`
▼	4	`set more off` `. set more off .`
	5
	6	`* specify directories where data are located and where results should be stored`
▼	7	`global dir_main : pwd` `. global dir_main : pwd .`
▼	8	`global dir_data "$dir_main/Data"` `global dir_data "/home/rstudio/repbox/projects_ejd/aer_112_9_9/mod/Scripts/Data" . global dir_data "$dir_main/Data" .`
▼	9	`global dir_results "$dir_main/Results"` `global dir_results "/home/rstudio/repbox/projects_ejd/aer_112_9_9/mod/Scripts/Results" . global dir_results "$dir_main/Results" .`
	10
	11
	12	`** Table 2: 5% significance treshold`
	13	`* read in the data`
▼	14	`cd "$dir_data"` `cd "/home/rstudio/repbox/projects_ejd/aer_112_9_9/mod/Scripts/Data" . cd "${repbox_path}/Data" /home/rstudio/repbox/projects_ejd/aer_112_9_9/mod/Data .`
▼	15	`capture use "MM_new.dta", clear` `. capture use "MM_new.dta", clear .`
	16
	17	`* determine folder to store results`
▼	18	`cd "$dir_results"` `cd "/home/rstudio/repbox/projects_ejd/aer_112_9_9/mod/Scripts/Results" . cd "${repbox_path}/Results" /home/rstudio/repbox/projects_ejd/aer_112_9_9/mod/Results .`
	19
	20
	21	`* drop obs with small significand`
▼	22	`keep if keep_obs==1` `. keep if keep_obs==1 (8,233 observations deleted) .`
	23
	24	`* first: 5% threshold`
	25
▼	26	`local depvar "sign_5pct"` `. local depvar "sign_5pct" .`
▼	27	`local threshold 1.96` `. local threshold 1.96 .`
▼	28	`local weight1 "pw="` `. local weight1 "pw=" .`
▼	29	`local weight2 "aw"` `. local weight2 "aw" .`
	30
	31
▼	32	`eststo clear` `. eststo clear .`
	33
▼	34	probit `depvar' DID IV RDD if t>(`threshold'-0.5) & t<(`threshold'+0.5) [`weight1'`weight2'], cluster(journal_article_cluster) probit sign_5pct DID IV RDD if t>(1.96-0.5) & t<(1.96+0.5) [pw=aw], cluster(journal_article_cluster) . probit `depvar' DID IV RDD if t>(`threshold'-0.5) & t<(`th > reshold'+0.5) [`weight1'`weight2'], cluster(journal_article_cluster) Iteration 0: log pseudolikelihood = -787128.03 Iteration 1: log pseudolikelihood = -783790.82 Iteration 2: log pseudolikelihood = -783790.8 Probit regression Number of obs = 3,558 Wald chi2(3) = 9.30 Prob > chi2 = 0.0256 Log pseudolikelihood = -783790.8 Pseudo R2 = 0.0042 (Std. err. adjusted for 464 clusters in journal_article_cluster) ------------------------------------------------------------------------------ \| Robust sign_5pct \| Coefficient std. err. z P>\|z\| [95% conf. interval] -------------+---------------------------------------------------------------- DID \| .1417897 .0981744 1.44 0.149 -.0506287 .334208 IV \| .2585744 .0882504 2.93 0.003 .0856068 .431542 RDD \| .2395807 .1623999 1.48 0.140 -.0787172 .5578786 _cons \| -.0147018 .058181 -0.25 0.801 -.1287345 .0993309 ------------------------------------------------------------------------------ .
▼	35	`eststo : margins, dydx() post` . eststo : margins, dydx() post Average marginal effects Number of obs = 3,558 Model VCE: Robust Expression: Pr(sign_5pct), predict() dy/dx wrt: DID IV RDD ------------------------------------------------------------------------------ \| Delta-method \| dy/dx std. err. z P>\|z\| [95% conf. interval] -------------+---------------------------------------------------------------- DID \| .0555643 .0383468 1.45 0.147 -.019594 .1307227 IV \| .1013297 .0340454 2.98 0.003 .0346019 .1680575 RDD \| .0938865 .0633513 1.48 0.138 -.0302798 .2180528 ------------------------------------------------------------------------------ (est1 stored) .
▼	36	estadd local Window "[`threshold'$\pm$0.50]" estadd local Window "[1.96$\pm$0.50]" . estadd local Window "[`threshold'$\pm$0.50]" added macro: e(Window) : "[1.96$\pm$0.50]" .
▼	37	sum `depvar' if t>(`threshold'-0.5) & t<(`threshold'+0.5) & method=="RCT" sum sign_5pct if t>(1.96-0.5) & t<(1.96+0.5) & method=="RCT" . sum `depvar' if t>(`threshold'-0.5) & t<(`threshold'+0.5) > & method=="RCT" Variable \| Obs Mean Std. dev. Min Max -------------+--------------------------------------------------------- sign_5pct \| 1,135 .4696035 .4992952 0 1 .
▼	38	`estadd local rct_sign = round(r(mean), 0.01)` `. estadd local rct_sign = round(r(mean), 0.01) added macro: e(rct_sign) : ".47" .`
	39
▼	40	probit `depvar' DID IV RDD top5 i.year experience_avg experience_avg_sq share_top_authors share_top_phd i.ireport authored_solo share_female_authors editor_present if t>(`threshold'-0.5) & t<(`threshold'+0.5) [`weight1'`weight2'], cluster(journal_article_cluster) probit sign_5pct DID IV RDD top5 i.year experience_avg experience_avg_sq share_top_authors share_top_phd i.ireport authored_solo share_female_authors editor_present if t>(1.96-0.5) & t<(1.96+0.5) [pw=aw], cluster(journal_article_cluster) . probit `depvar' DID IV RDD top5 i.year experience_avg expe > rience_avg_sq share_top_authors share_top_phd i.ireport authored_solo share_f > emale_authors editor_present if t>(`threshold'-0.5) & t<(`threshold'+0.5) [`w > eight1'`weight2'], cluster(journal_article_cluster) Iteration 0: log pseudolikelihood = -787128.03 Iteration 1: log pseudolikelihood = -779397.93 Iteration 2: log pseudolikelihood = -779397.22 Iteration 3: log pseudolikelihood = -779397.22 Probit regression Number of obs = 3,558 Wald chi2(15) = 17.30 Prob > chi2 = 0.3015 Log pseudolikelihood = -779397.22 Pseudo R2 = 0.0098 (Std. err. adjusted for 464 clusters in journal_article_cluster) ------------------------------------------------------------------------------ \| Robust sign_5pct \| Coefficient std. err. z P>\|z\| [95% conf. interval] -------------+---------------------------------------------------------------- DID \| .1165539 .1006179 1.16 0.247 -.0806535 .3137613 IV \| .2561537 .0955064 2.68 0.007 .0689646 .4433428 RDD \| .2115284 .1575675 1.34 0.179 -.0972981 .5203549 top5 \| -.0722586 .1376952 -0.52 0.600 -.3421362 .197619 \| year \| 2018 \| .0158176 .084099 0.19 0.851 -.1490134 .1806487 \| experience~g \| -.0195206 .021143 -0.92 0.356 -.0609601 .0219188 experience~q \| .0058338 .0547813 0.11 0.915 -.1015356 .1132032 share_top_~s \| -.0035355 .1397164 -0.03 0.980 -.2773747 .2703037 share_top_~d \| .0370752 .1147796 0.32 0.747 -.1878887 .2620391 \| ireport \| 2 \| -.1032901 .3110685 -0.33 0.740 -.7129732 .5063929 3 \| -.1859905 .2622382 -0.71 0.478 -.6999679 .3279869 4 \| -.1515877 .2895918 -0.52 0.601 -.7191771 .4160017 \| authored_s~o \| -.2043409 .1288895 -1.59 0.113 -.4569596 .0482778 share_fema~s \| -.0633343 .1384035 -0.46 0.647 -.3346001 .2079316 editor_pre~t \| .0592437 .1213527 0.49 0.625 -.1786032 .2970906 _cons \| .3775107 .3603338 1.05 0.295 -.3287307 1.083752 ------------------------------------------------------------------------------ .
▼	41	`eststo : margins, dydx() post` . eststo : margins, dydx() post Average marginal effects Number of obs = 3,558 Model VCE: Robust Expression: Pr(sign_5pct), predict() dy/dx wrt: DID IV RDD top5 2018.year experience_avg experience_avg_sq share_top_authors share_top_phd 2.ireport 3.ireport 4.ireport authored_solo share_female_authors editor_present ------------------------------------------------------------------------------ \| Delta-method \| dy/dx std. err. z P>\|z\| [95% conf. interval] -------------+---------------------------------------------------------------- DID \| .0453942 .0390883 1.16 0.246 -.0312175 .1220059 IV \| .099764 .0366758 2.72 0.007 .0278807 .1716474 RDD \| .0823838 .0611258 1.35 0.178 -.0374206 .2021883 top5 \| -.0281425 .053614 -0.52 0.600 -.1332241 .076939 \| year \| 2018 \| .0061621 .0327656 0.19 0.851 -.0580573 .0703814 \| experience~g \| -.0076027 .0082208 -0.92 0.355 -.0237152 .0085098 experience~q \| .0022721 .0213344 0.11 0.915 -.0395426 .0440867 share_top_~s \| -.001377 .0544148 -0.03 0.980 -.1080279 .105274 share_top_~d \| .0144396 .044689 0.32 0.747 -.0731492 .1020284 \| ireport \| 2 \| -.039136 .1171979 -0.33 0.738 -.2688396 .1905677 3 \| -.0711716 .0979541 -0.73 0.467 -.2631582 .1208149 4 \| -.0577843 .1090707 -0.53 0.596 -.2715589 .1559903 \| authored_s~o \| -.0795845 .0499084 -1.59 0.111 -.1774031 .018234 share_fema~s \| -.0246668 .0539276 -0.46 0.647 -.130363 .0810295 editor_pre~t \| .0230736 .0472585 0.49 0.625 -.0695513 .1156985 ------------------------------------------------------------------------------ Note: dy/dx for factor levels is the discrete change from the base level. (est2 stored) .
▼	42	estadd local Window "[`threshold'$\pm$0.50]" estadd local Window "[1.96$\pm$0.50]" . estadd local Window "[`threshold'$\pm$0.50]" added macro: e(Window) : "[1.96$\pm$0.50]" .
▼	43	sum `depvar' if t>(`threshold'-0.5) & t<(`threshold'+0.5) & method=="RCT" sum sign_5pct if t>(1.96-0.5) & t<(1.96+0.5) & method=="RCT" . sum `depvar' if t>(`threshold'-0.5) & t<(`threshold'+0.5) > & method=="RCT" Variable \| Obs Mean Std. dev. Min Max -------------+--------------------------------------------------------- sign_5pct \| 1,135 .4696035 .4992952 0 1 .
▼	44	`estadd local rct_sign = round(r(mean), 0.01)` `. estadd local rct_sign = round(r(mean), 0.01) added macro: e(rct_sign) : ".47" .`
	45
▼	46	probit `depvar' DID IV RDD top5 i.year FINANCE MACRO_GROWTH GEN_INT EXP DEV LABOR PUB URB experience_avg experience_avg_sq share_top_authors share_top_phd i.ireport authored_solo share_female_authors editor_present if t>(`threshold'-0.5) & t<(`threshold'+0.5) [`weight1'`weight2'], cluster(journal_article_cluster) probit sign_5pct DID IV RDD top5 i.year FINANCE MACRO_GROWTH GEN_INT EXP DEV LABOR PUB URB experience_avg experience_avg_sq share_top_authors share_top_phd i.ireport authored_solo share_female_authors editor_present if t>(1.96-0.5) & t<(1.96+0.5) [pw=aw], cluster(journal_article_cluster) . probit `depvar' DID IV RDD top5 i.year FINANCE MACRO_GROWT > H GEN_INT EXP DEV LABOR PUB URB experience_avg experience_avg_sq share_top_au > thors share_top_phd i.ireport authored_solo share_female_authors editor_prese > nt if t>(`threshold'-0.5) & t<(`threshold'+0.5) [`weight1'`weight2'], cluster > (journal_article_cluster) Iteration 0: log pseudolikelihood = -787128.03 Iteration 1: log pseudolikelihood = -771481.98 Iteration 2: log pseudolikelihood = -771472.86 Iteration 3: log pseudolikelihood = -771472.86 Probit regression Number of obs = 3,558 Wald chi2(23) = 28.71 Prob > chi2 = 0.1901 Log pseudolikelihood = -771472.86 Pseudo R2 = 0.0199 (Std. err. adjusted for 464 clusters in journal_article_cluster) ------------------------------------------------------------------------------ \| Robust sign_5pct \| Coefficient std. err. z P>\|z\| [95% conf. interval] -------------+---------------------------------------------------------------- DID \| .0757119 .1041663 0.73 0.467 -.1284502 .279874 IV \| .2051944 .099425 2.06 0.039 .010325 .4000639 RDD \| .1788154 .1514817 1.18 0.238 -.1180833 .475714 top5 \| -.0536747 .2860662 -0.19 0.851 -.6143542 .5070048 \| year \| 2018 \| .0326287 .0860954 0.38 0.705 -.1361151 .2013725 \| FINANCE \| .2836399 .2923781 0.97 0.332 -.2894106 .8566905 MACRO_GROWTH \| .1591018 .305504 0.52 0.603 -.439675 .7578786 GEN_INT \| .0357906 .2600287 0.14 0.891 -.4738562 .5454374 EXP \| -.1864556 .297199 -0.63 0.530 -.7689549 .3960438 DEV \| -.1670997 .2850511 -0.59 0.558 -.7257896 .3915902 LABOR \| -.0488808 .306058 -0.16 0.873 -.6487433 .5509818 PUB \| -.111524 .2683149 -0.42 0.678 -.6374116 .4143635 URB \| -.3861322 .3149989 -1.23 0.220 -1.003519 .2312543 experience~g \| -.0346788 .0220463 -1.57 0.116 -.0778888 .0085311 experience~q \| .0451448 .0575547 0.78 0.433 -.0676603 .1579499 share_top_~s \| .0068984 .136691 0.05 0.960 -.2610111 .2748078 share_top_~d \| -.0349392 .1161714 -0.30 0.764 -.2626309 .1927525 \| ireport \| 2 \| -.2030917 .3086295 -0.66 0.511 -.8079945 .401811 3 \| -.1921778 .2649042 -0.73 0.468 -.7113804 .3270249 4 \| -.3767746 .3121362 -1.21 0.227 -.9885502 .235001 \| authored_s~o \| -.2774233 .1325264 -2.09 0.036 -.5371703 -.0176764 share_fema~s \| -.0409916 .1291988 -0.32 0.751 -.2942166 .2122335 editor_pre~t \| .059749 .1226511 0.49 0.626 -.1806428 .3001408 _cons \| .5575802 .4590339 1.21 0.224 -.3421097 1.45727 ------------------------------------------------------------------------------ .
▼	47	`eststo : margins, dydx() post` . eststo : margins, dydx() post Average marginal effects Number of obs = 3,558 Model VCE: Robust Expression: Pr(sign_5pct), predict() dy/dx wrt: DID IV RDD top5 2018.year FINANCE MACRO_GROWTH GEN_INT EXP DEV LABOR PUB URB experience_avg experience_avg_sq share_top_authors share_top_phd 2.ireport 3.ireport 4.ireport authored_solo share_female_authors editor_present ------------------------------------------------------------------------------ \| Delta-method \| dy/dx std. err. z P>\|z\| [95% conf. interval] -------------+---------------------------------------------------------------- DID \| .0291632 .0401224 0.73 0.467 -.0494752 .1078016 IV \| .0790381 .0379999 2.08 0.038 .0045596 .1535166 RDD \| .0688772 .0581974 1.18 0.237 -.0451876 .1829421 top5 \| -.0206748 .1101918 -0.19 0.851 -.2366467 .1952972 \| year \| 2018 \| .0125738 .0331962 0.38 0.705 -.0524896 .0776371 \| FINANCE \| .1092542 .1122214 0.97 0.330 -.1106957 .3292042 MACRO_GROWTH \| .0612838 .1176928 0.52 0.603 -.1693897 .2919574 GEN_INT \| .013786 .1001594 0.14 0.891 -.1825227 .2100948 EXP \| -.0718201 .114333 -0.63 0.530 -.2959087 .1522685 DEV \| -.0643645 .1097413 -0.59 0.558 -.2794535 .1507245 LABOR \| -.0188282 .1178808 -0.16 0.873 -.2498704 .212214 PUB \| -.0429575 .1033144 -0.42 0.678 -.2454501 .159535 URB \| -.1487329 .1210878 -1.23 0.219 -.3860606 .0885949 experience~g \| -.0133578 .0084511 -1.58 0.114 -.0299217 .0032061 experience~q \| .0173892 .0221389 0.79 0.432 -.0260022 .0607805 share_top_~s \| .0026572 .0526548 0.05 0.960 -.1005443 .1058586 share_top_~d \| -.0134581 .0447383 -0.30 0.764 -.1011436 .0742274 \| ireport \| 2 \| -.0760581 .1138294 -0.67 0.504 -.2991597 .1470435 3 \| -.0718773 .0963194 -0.75 0.456 -.2606598 .1169051 4 \| -.1433133 .1151492 -1.24 0.213 -.3690015 .082375 \| authored_s~o \| -.1068597 .0504076 -2.12 0.034 -.2056569 -.0080625 share_fema~s \| -.0157894 .0497791 -0.32 0.751 -.1133546 .0817758 editor_pre~t \| .0230145 .0472671 0.49 0.626 -.0696273 .1156563 ------------------------------------------------------------------------------ Note: dy/dx for factor levels is the discrete change from the base level. (est3 stored) .
▼	48	estadd local Window "[`threshold'$\pm$0.50]" estadd local Window "[1.96$\pm$0.50]" . estadd local Window "[`threshold'$\pm$0.50]" added macro: e(Window) : "[1.96$\pm$0.50]" .
▼	49	sum `depvar' if t>(`threshold'-0.5) & t<(`threshold'+0.5) & method=="RCT" sum sign_5pct if t>(1.96-0.5) & t<(1.96+0.5) & method=="RCT" . sum `depvar' if t>(`threshold'-0.5) & t<(`threshold'+0.5) > & method=="RCT" Variable \| Obs Mean Std. dev. Min Max -------------+--------------------------------------------------------- sign_5pct \| 1,135 .4696035 .4992952 0 1 .
▼	50	`estadd local rct_sign = round(r(mean), 0.01)` `. estadd local rct_sign = round(r(mean), 0.01) added macro: e(rct_sign) : ".47" .`
	51
▼	52	probit `depvar' DID IV RDD i.year i.unique_j experience_avg experience_avg_sq share_top_authors share_top_phd i.ireport authored_solo share_female_authors editor_present if t>(`threshold'-0.5) & t<(`threshold'+0.5) [`weight1'`weight2'], cluster(journal_article_cluster) probit sign_5pct DID IV RDD i.year i.unique_j experience_avg experience_avg_sq share_top_authors share_top_phd i.ireport authored_solo share_female_authors editor_present if t>(1.96-0.5) & t<(1.96+0.5) [pw=aw], cluster(journal_article_cluster) . probit `depvar' DID IV RDD i.year i.unique_j experience_av > g experience_avg_sq share_top_authors share_top_phd i.ireport authored_solo s > hare_female_authors editor_present if t>(`threshold'-0.5) & t<(`threshold'+0. > 5) [`weight1'`weight2'], cluster(journal_article_cluster) Iteration 0: log pseudolikelihood = -787128.03 Iteration 1: log pseudolikelihood = -766548.66 Iteration 2: log pseudolikelihood = -766512.36 Iteration 3: log pseudolikelihood = -766512.36 Probit regression Number of obs = 3,558 Wald chi2(38) = 46.69 Prob > chi2 = 0.1574 Log pseudolikelihood = -766512.36 Pseudo R2 = 0.0262 (Std. err. adjusted for 464 clusters in journal_article_cluster) ------------------------------------------------------------------------------ \| Robust sign_5pct \| Coefficient std. err. z P>\|z\| [95% conf. interval] -------------+---------------------------------------------------------------- DID \| .0736408 .1062244 0.69 0.488 -.1345553 .2818368 IV \| .2198465 .0995092 2.21 0.027 .024812 .4148809 RDD \| .1801098 .1524099 1.18 0.237 -.118608 .4788277 \| year \| 2018 \| .0566411 .0896519 0.63 0.528 -.1190734 .2323557 \| unique_j \| 2 \| -.2516936 .2134245 -1.18 0.238 -.6699979 .1666107 3 \| .0785309 .3926721 0.20 0.841 -.6910922 .848154 4 \| .2345425 .2341113 1.00 0.316 -.2243073 .6933923 5 \| .0482819 .3622297 0.13 0.894 -.6616753 .7582392 6 \| .5010829 .6140697 0.82 0.414 -.7024715 1.704637 7 \| .1438332 .2350388 0.61 0.541 -.3168343 .6045007 8 \| .1433989 .2249147 0.64 0.524 -.2974259 .5842237 9 \| .0323671 .2624939 0.12 0.902 -.4821115 .5468457 10 \| -.0738271 .2192112 -0.34 0.736 -.5034732 .355819 11 \| .0311221 .1876327 0.17 0.868 -.3366312 .3988753 12 \| .5293393 .2383176 2.22 0.026 .0622454 .9964331 13 \| .4821917 .2814032 1.71 0.087 -.0693484 1.033732 14 \| .0384885 .2951909 0.13 0.896 -.540075 .6170519 15 \| -.0118614 .2480466 -0.05 0.962 -.4980239 .4743011 16 \| .2766264 .2430563 1.14 0.255 -.1997553 .753008 17 \| -.1370631 .2146993 -0.64 0.523 -.5578661 .2837398 18 \| -.1239927 .1897303 -0.65 0.513 -.4958572 .2478718 19 \| .0051459 .2340717 0.02 0.982 -.4536262 .463918 20 \| -.1338312 .3528399 -0.38 0.704 -.8253847 .5577223 21 \| .3127046 .5474384 0.57 0.568 -.7602549 1.385664 22 \| -.1507644 .2243116 -0.67 0.502 -.5904071 .2888783 23 \| .0338202 .2392322 0.14 0.888 -.4350662 .5027067 24 \| -.3245505 .2433748 -1.33 0.182 -.8015562 .1524553 25 \| -.0880728 .1809318 -0.49 0.626 -.4426925 .2665469 \| experience~g \| -.0345579 .0220377 -1.57 0.117 -.0777511 .0086353 experience~q \| .0516204 .057724 0.89 0.371 -.0615166 .1647575 share_top_~s \| .0046775 .1347783 0.03 0.972 -.2594831 .2688381 share_top_~d \| -.0335067 .1192466 -0.28 0.779 -.2672257 .2002124 \| ireport \| 2 \| .0220078 .5879276 0.04 0.970 -1.130309 1.174325 3 \| .0415578 .5676137 0.07 0.942 -1.070945 1.15406 4 \| -.1325214 .5967744 -0.22 0.824 -1.302178 1.037135 \| authored_s~o \| -.2185934 .1364597 -1.60 0.109 -.4860496 .0488627 share_fema~s \| -.0108071 .1256119 -0.09 0.931 -.2570019 .2353877 editor_pre~t \| .0925139 .1263826 0.73 0.464 -.1551914 .3402192 _cons \| .2000555 .6305136 0.32 0.751 -1.035729 1.435839 ------------------------------------------------------------------------------ .
▼	53	`eststo : margins, dydx() post` . eststo : margins, dydx() post Average marginal effects Number of obs = 3,558 Model VCE: Robust Expression: Pr(sign_5pct), predict() dy/dx wrt: DID IV RDD 2018.year 2.unique_j 3.unique_j 4.unique_j 5.unique_j 6.unique_j 7.unique_j 8.unique_j 9.unique_j 10.unique_j 11.unique_j 12.unique_j 13.unique_j 14.unique_j 15.unique_j 16.unique_j 17.unique_j 18.unique_j 19.unique_j 20.unique_j 21.unique_j 22.unique_j 23.unique_j 24.unique_j 25.unique_j experience_avg experience_avg_sq share_top_authors share_top_phd 2.ireport 3.ireport 4.ireport authored_solo share_female_authors editor_present ------------------------------------------------------------------------------ \| Delta-method \| dy/dx std. err. z P>\|z\| [95% conf. interval] -------------+---------------------------------------------------------------- DID \| .0281719 .0406646 0.69 0.488 -.0515293 .107873 IV \| .084104 .0377267 2.23 0.026 .010161 .158047 RDD \| .0689024 .0582121 1.18 0.237 -.0451912 .182996 \| year \| 2018 \| .0216803 .0343569 0.63 0.528 -.045658 .0890186 \| unique_j \| 2 \| -.0989098 .0835062 -1.18 0.236 -.262579 .0647593 3 \| .0306391 .1525348 0.20 0.841 -.2683236 .3296017 4 \| .0900873 .0891744 1.01 0.312 -.0846912 .2648658 5 \| .0188776 .1413106 0.13 0.894 -.258086 .2958412 6 \| .1841719 .2051616 0.90 0.369 -.2179374 .5862812 7 \| .0558032 .0909217 0.61 0.539 -.1224001 .2340066 8 \| .0556371 .0870941 0.64 0.523 -.1150643 .2263384 9 \| .0126678 .1026468 0.12 0.902 -.1885162 .2138519 10 \| -.0290274 .086141 -0.34 0.736 -.1978607 .1398058 11 \| .0121814 .0734644 0.17 0.868 -.1318061 .1561689 12 \| .1934162 .08424 2.30 0.022 .0283088 .3585236 13 \| .1779048 .0991036 1.80 0.073 -.0163348 .3721443 14 \| .0150579 .115359 0.13 0.896 -.2110416 .2411574 15 \| -.0046533 .0973201 -0.05 0.962 -.1953972 .1860906 16 \| .1056657 .0917448 1.15 0.249 -.0741509 .2854823 17 \| -.0539442 .0843527 -0.64 0.522 -.2192724 .111384 18 \| -.0487952 .0745362 -0.65 0.513 -.1948835 .097293 19 \| .0020171 .091746 0.02 0.982 -.1778017 .1818359 20 \| -.0526712 .1389144 -0.38 0.705 -.3249384 .219596 21 \| .1188302 .1996676 0.60 0.552 -.2725111 .5101716 22 \| -.0593392 .0881722 -0.67 0.501 -.2321536 .1134751 23 \| .0132354 .0935735 0.14 0.888 -.1701653 .196636 24 \| -.1271377 .0943687 -1.35 0.178 -.3120969 .0578216 25 \| -.0346403 .0710473 -0.49 0.626 -.1738903 .1046098 \| experience~g \| -.0132204 .0083953 -1.57 0.115 -.0296749 .0032341 experience~q \| .0197478 .0220502 0.90 0.370 -.0234697 .0629653 share_top_~s \| .0017894 .0515635 0.03 0.972 -.0992733 .1028521 share_top_~d \| -.0128182 .0456253 -0.28 0.779 -.1022421 .0766057 \| ireport \| 2 \| .0084063 .2248797 0.04 0.970 -.4323497 .4491624 3 \| .0158495 .2171473 0.07 0.942 -.4097514 .4414505 4 \| -.051024 .2284281 -0.22 0.823 -.4987348 .3966868 \| authored_s~o \| -.0836246 .0517545 -1.62 0.106 -.1850616 .0178124 share_fema~s \| -.0041344 .0480566 -0.09 0.931 -.0983236 .0900549 editor_pre~t \| .0353919 .0484033 0.73 0.465 -.0594769 .1302607 ------------------------------------------------------------------------------ Note: dy/dx for factor levels is the discrete change from the base level. (est4 stored) .
▼	54	estadd local Window "[`threshold'$\pm$0.50]" estadd local Window "[1.96$\pm$0.50]" . estadd local Window "[`threshold'$\pm$0.50]" added macro: e(Window) : "[1.96$\pm$0.50]" .
▼	55	sum `depvar' if t>(`threshold'-0.5) & t<(`threshold'+0.5) & method=="RCT" sum sign_5pct if t>(1.96-0.5) & t<(1.96+0.5) & method=="RCT" . sum `depvar' if t>(`threshold'-0.5) & t<(`threshold'+0.5) > & method=="RCT" Variable \| Obs Mean Std. dev. Min Max -------------+--------------------------------------------------------- sign_5pct \| 1,135 .4696035 .4992952 0 1 .
▼	56	`estadd local rct_sign = round(r(mean), 0.01)` `. estadd local rct_sign = round(r(mean), 0.01) added macro: e(rct_sign) : ".47" .`
	57
▼	58	probit `depvar' DID IV RDD i.year i.unique_j experience_avg experience_avg_sq share_top_authors share_top_phd i.ireport authored_solo share_female_authors editor_present if t>(`threshold'-0.35) & t<(`threshold'+0.35) [`weight1'`weight2'], cluster(journal_article_cluster) probit sign_5pct DID IV RDD i.year i.unique_j experience_avg experience_avg_sq share_top_authors share_top_phd i.ireport authored_solo share_female_authors editor_present if t>(1.96-0.35) & t<(1.96+0.35) [pw=aw], cluster(journal_article_cluster) . probit `depvar' DID IV RDD i.year i.unique_j experience_av > g experience_avg_sq share_top_authors share_top_phd i.ireport authored_solo s > hare_female_authors editor_present if t>(`threshold'-0.35) & t<(`threshold'+0 > .35) [`weight1'`weight2'], cluster(journal_article_cluster) note: 6.unique_j != 0 predicts success perfectly; 6.unique_j omitted and 2 obs not used. Iteration 0: log pseudolikelihood = -591666.24 Iteration 1: log pseudolikelihood = -574775.18 Iteration 2: log pseudolikelihood = -574730.73 Iteration 3: log pseudolikelihood = -574730.72 Probit regression Number of obs = 2,626 Wald chi2(37) = 50.33 Prob > chi2 = 0.0707 Log pseudolikelihood = -574730.72 Pseudo R2 = 0.0286 (Std. err. adjusted for 433 clusters in journal_article_cluster) ------------------------------------------------------------------------------ \| Robust sign_5pct \| Coefficient std. err. z P>\|z\| [95% conf. interval] -------------+---------------------------------------------------------------- DID \| .0633271 .118004 0.54 0.592 -.1679564 .2946106 IV \| .2543622 .1094703 2.32 0.020 .0398044 .46892 RDD \| .1921999 .1575691 1.22 0.223 -.1166298 .5010297 \| year \| 2018 \| -.0104169 .0969474 -0.11 0.914 -.2004303 .1795966 \| unique_j \| 2 \| -.0266616 .2970691 -0.09 0.928 -.6089064 .5555832 3 \| .2681497 .4806622 0.56 0.577 -.6739309 1.21023 4 \| .0025828 .3186021 0.01 0.994 -.6218658 .6270314 5 \| .160241 .4015092 0.40 0.690 -.6267025 .9471846 7 \| .1514289 .2809237 0.54 0.590 -.3991713 .7020291 8 \| .2737456 .2835051 0.97 0.334 -.2819141 .8294053 9 \| .1358753 .3272474 0.42 0.678 -.5055179 .7772684 10 \| -.0917075 .2500014 -0.37 0.714 -.5817011 .3982862 11 \| .1614007 .2497478 0.65 0.518 -.3280961 .6508974 12 \| .6870897 .3070947 2.24 0.025 .0851951 1.288984 13 \| .5541148 .302435 1.83 0.067 -.0386469 1.146877 14 \| .1863834 .3771267 0.49 0.621 -.5527713 .9255381 15 \| .3124553 .3026538 1.03 0.302 -.2807351 .9056458 16 \| .025289 .3274312 0.08 0.938 -.6164644 .6670424 17 \| -.2197718 .2748699 -0.80 0.424 -.7585068 .3189632 18 \| .1824681 .2524869 0.72 0.470 -.3123971 .6773332 19 \| .1042038 .2800405 0.37 0.710 -.4446655 .6530732 20 \| -.1810595 .4365845 -0.41 0.678 -1.03675 .6746305 21 \| .9323148 .5237417 1.78 0.075 -.0942001 1.95883 22 \| -.0170097 .2992592 -0.06 0.955 -.603547 .5695275 23 \| .0793226 .3102112 0.26 0.798 -.5286802 .6873254 24 \| -.1313301 .3273032 -0.40 0.688 -.7728327 .5101724 25 \| .0436462 .250565 0.17 0.862 -.4474522 .5347445 \| experience~g \| -.0274967 .0252185 -1.09 0.276 -.076924 .0219307 experience~q \| .0513463 .0677197 0.76 0.448 -.0813819 .1840746 share_top_~s \| -.1034644 .1545477 -0.67 0.503 -.4063724 .1994436 share_top_~d \| .151753 .1320918 1.15 0.251 -.1071422 .4106482 \| ireport \| 2 \| .4059452 .5446588 0.75 0.456 -.6615664 1.473457 3 \| .407311 .5162205 0.79 0.430 -.6044627 1.419085 4 \| .5783056 .5491737 1.05 0.292 -.4980551 1.654666 \| authored_s~o \| -.2579011 .1374657 -1.88 0.061 -.5273288 .0115266 share_fema~s \| -.0167991 .1323454 -0.13 0.899 -.2761913 .242593 editor_pre~t \| .0464266 .1229163 0.38 0.706 -.1944849 .2873382 _cons \| -.3689419 .5905684 -0.62 0.532 -1.526435 .788551 ------------------------------------------------------------------------------ .
▼	59	`eststo : margins, dydx() post` . eststo : margins, dydx() post Average marginal effects Number of obs = 2,626 Model VCE: Robust Expression: Pr(sign_5pct), predict() dy/dx wrt: DID IV RDD 2018.year 2.unique_j 3.unique_j 4.unique_j 5.unique_j 7.unique_j 8.unique_j 9.unique_j 10.unique_j 11.unique_j 12.unique_j 13.unique_j 14.unique_j 15.unique_j 16.unique_j 17.unique_j 18.unique_j 19.unique_j 20.unique_j 21.unique_j 22.unique_j 23.unique_j 24.unique_j 25.unique_j experience_avg experience_avg_sq share_top_authors share_top_phd 2.ireport 3.ireport 4.ireport authored_solo share_female_authors editor_present ------------------------------------------------------------------------------ \| Delta-method \| dy/dx std. err. z P>\|z\| [95% conf. interval] -------------+---------------------------------------------------------------- DID \| .0242441 .0451488 0.54 0.591 -.0642459 .1127341 IV \| .0973798 .0413972 2.35 0.019 .0162428 .1785168 RDD \| .0735816 .0601929 1.22 0.222 -.0443944 .1915577 \| year \| 2018 \| -.0039875 .0371007 -0.11 0.914 -.0767035 .0687285 \| unique_j \| 2 \| -.0104825 .1167964 -0.09 0.928 -.2393993 .2184343 3 \| .1044124 .1844381 0.57 0.571 -.2570797 .4659045 4 \| .0010158 .1253027 0.01 0.994 -.2445729 .2466044 5 \| .0628198 .1567737 0.40 0.689 -.2444511 .3700906 7 \| .0593883 .1102345 0.54 0.590 -.1566674 .275444 8 \| .1065431 .1102239 0.97 0.334 -.1094919 .322578 9 \| .0533218 .1281341 0.42 0.677 -.1978165 .3044601 10 \| -.0359973 .0982164 -0.37 0.714 -.2284979 .1565032 11 \| .063271 .0979908 0.65 0.518 -.1287875 .2553295 12 \| .2519214 .1102311 2.29 0.022 .0358724 .4679704 13 \| .20824 .1126418 1.85 0.065 -.0125339 .4290139 14 \| .0729733 .1469962 0.50 0.620 -.2151341 .3610806 15 \| .121196 .1168873 1.04 0.300 -.1078989 .3502909 16 \| .0099462 .1287847 0.08 0.938 -.2424671 .2623594 17 \| -.0856451 .107071 -0.80 0.424 -.2955004 .1242102 18 \| .0714553 .0989787 0.72 0.470 -.1225393 .2654499 19 \| .0409353 .1099623 0.37 0.710 -.1745868 .2564574 20 \| -.0707522 .1694953 -0.42 0.676 -.4029569 .2614525 21 \| .3226878 .1499695 2.15 0.031 .028753 .6166226 22 \| -.0066886 .1176768 -0.06 0.955 -.2373309 .2239538 23 \| .0311793 .1218641 0.26 0.798 -.20767 .2700286 24 \| -.0514641 .1280655 -0.40 0.688 -.3024678 .1995397 25 \| .0171644 .0985253 0.17 0.862 -.1759415 .2102704 \| experience~g \| -.0105268 .0096251 -1.09 0.274 -.0293916 .008338 experience~q \| .0196574 .0258859 0.76 0.448 -.0310781 .0703928 share_top_~s \| -.0396102 .0590569 -0.67 0.502 -.1553596 .0761392 share_top_~d \| .058097 .0503718 1.15 0.249 -.04063 .156824 \| ireport \| 2 \| .1555973 .203309 0.77 0.444 -.242881 .5540757 3 \| .1561221 .1920849 0.81 0.416 -.2203574 .5326016 4 \| .2208672 .2041461 1.08 0.279 -.1792518 .6209861 \| authored_s~o \| -.0987346 .0523303 -1.89 0.059 -.2013002 .003831 share_fema~s \| -.0064314 .0506837 -0.13 0.899 -.1057695 .0929068 editor_pre~t \| .0177739 .0470249 0.38 0.705 -.0743933 .1099411 ------------------------------------------------------------------------------ Note: dy/dx for factor levels is the discrete change from the base level. (est5 stored) .
▼	60	estadd local Window "[`threshold'$\pm$0.35]" estadd local Window "[1.96$\pm$0.35]" . estadd local Window "[`threshold'$\pm$0.35]" added macro: e(Window) : "[1.96$\pm$0.35]" .
▼	61	sum `depvar' if t>(`threshold'-0.35) & t<(`threshold'+0.35) & method=="RCT" sum sign_5pct if t>(1.96-0.35) & t<(1.96+0.35) & method=="RCT" . sum `depvar' if t>(`threshold'-0.35) & t<(`threshold'+0.35 > ) & method=="RCT" Variable \| Obs Mean Std. dev. Min Max -------------+--------------------------------------------------------- sign_5pct \| 829 .4788902 .4998558 0 1 .
▼	62	`estadd local rct_sign = round(r(mean), 0.01)` `. estadd local rct_sign = round(r(mean), 0.01) added macro: e(rct_sign) : ".48" .`
	63
▼	64	probit `depvar' DID IV RDD i.year i.unique_j experience_avg experience_avg_sq share_top_authors share_top_phd i.ireport authored_solo share_female_authors editor_present if t>(`threshold'-0.2) & t<(`threshold'+0.2) [`weight1'`weight2'], cluster(journal_article_cluster) probit sign_5pct DID IV RDD i.year i.unique_j experience_avg experience_avg_sq share_top_authors share_top_phd i.ireport authored_solo share_female_authors editor_present if t>(1.96-0.2) & t<(1.96+0.2) [pw=aw], cluster(journal_article_cluster) . probit `depvar' DID IV RDD i.year i.unique_j experience_av > g experience_avg_sq share_top_authors share_top_phd i.ireport authored_solo s > hare_female_authors editor_present if t>(`threshold'-0.2) & t<(`threshold'+0. > 2) [`weight1'`weight2'], cluster(journal_article_cluster) note: 1.ireport != 0 predicts success perfectly; 1.ireport omitted and 2 obs not used. note: 4.ireport omitted because of collinearity. Iteration 0: log pseudolikelihood = -355463.65 Iteration 1: log pseudolikelihood = -339163.89 Iteration 2: log pseudolikelihood = -339074.16 Iteration 3: log pseudolikelihood = -339074.15 Probit regression Number of obs = 1,585 Wald chi2(35) = 39.48 Prob > chi2 = 0.2764 Log pseudolikelihood = -339074.15 Pseudo R2 = 0.0461 (Std. err. adjusted for 382 clusters in journal_article_cluster) ------------------------------------------------------------------------------ \| Robust sign_5pct \| Coefficient std. err. z P>\|z\| [95% conf. interval] -------------+---------------------------------------------------------------- DID \| -.0964881 .1567822 -0.62 0.538 -.4037756 .2107994 IV \| .2509065 .1353012 1.85 0.064 -.0142791 .5160921 RDD \| .1044717 .1944235 0.54 0.591 -.2765913 .4855346 \| year \| 2018 \| .0628803 .1083788 0.58 0.562 -.1495382 .2752989 \| unique_j \| 2 \| .4421289 .4739418 0.93 0.351 -.4867799 1.371038 3 \| .7663616 .5749897 1.33 0.183 -.3605975 1.893321 4 \| .1554897 .3627346 0.43 0.668 -.5554571 .8664365 5 \| -.2566929 .3436636 -0.75 0.455 -.9302612 .4168754 7 \| .4169843 .3798307 1.10 0.272 -.3274701 1.161439 8 \| .2814138 .3223887 0.87 0.383 -.3504565 .9132841 9 \| .5996322 .3628387 1.65 0.098 -.1115185 1.310783 10 \| -.1096609 .3375951 -0.32 0.745 -.7713352 .5520134 11 \| .1573383 .3404936 0.46 0.644 -.510017 .8246935 12 \| .6283063 .3999799 1.57 0.116 -.1556398 1.412253 13 \| .7346479 .3554657 2.07 0.039 .0379479 1.431348 14 \| .6212516 .4990812 1.24 0.213 -.3569297 1.599433 15 \| .3771099 .3620881 1.04 0.298 -.3325698 1.08679 16 \| .348219 .3378403 1.03 0.303 -.3139358 1.010374 17 \| -1.332629 .8223676 -1.62 0.105 -2.94444 .2791815 18 \| .283486 .3003785 0.94 0.345 -.3052451 .8722171 19 \| .4831164 .3747499 1.29 0.197 -.2513799 1.217613 20 \| .1832293 .5441272 0.34 0.736 -.8832405 1.249699 21 \| .1381565 .32404 0.43 0.670 -.4969502 .7732632 22 \| .030599 .3645257 0.08 0.933 -.6838582 .7450562 23 \| .2263885 .3299362 0.69 0.493 -.4202745 .8730515 24 \| .1596085 .3719585 0.43 0.668 -.5694168 .8886338 25 \| .1191819 .3098103 0.38 0.700 -.4880351 .7263989 \| experience~g \| -.0005587 .0296723 -0.02 0.985 -.0587152 .0575979 experience~q \| -.0114865 .0853756 -0.13 0.893 -.1788197 .1558466 share_top_~s \| -.2123991 .1831683 -1.16 0.246 -.5714024 .1466041 share_top_~d \| .3849395 .1648651 2.33 0.020 .0618099 .7080692 \| ireport \| 3 \| .1116569 .1444979 0.77 0.440 -.1715539 .3948676 4 \| 0 (omitted) \| authored_s~o \| -.1546806 .1687515 -0.92 0.359 -.4854274 .1760662 share_fema~s \| -.0163136 .1540992 -0.11 0.916 -.3183424 .2857153 editor_pre~t \| -.0630015 .154652 -0.41 0.684 -.3661138 .2401108 _cons \| -.3815988 .3556943 -1.07 0.283 -1.078747 .3155493 ------------------------------------------------------------------------------ .
▼	65	`eststo : margins, dydx() post` . eststo : margins, dydx() post Average marginal effects Number of obs = 1,585 Model VCE: Robust Expression: Pr(sign_5pct), predict() dy/dx wrt: DID IV RDD 2018.year 2.unique_j 3.unique_j 4.unique_j 5.unique_j 7.unique_j 8.unique_j 9.unique_j 10.unique_j 11.unique_j 12.unique_j 13.unique_j 14.unique_j 15.unique_j 16.unique_j 17.unique_j 18.unique_j 19.unique_j 20.unique_j 21.unique_j 22.unique_j 23.unique_j 24.unique_j 25.unique_j experience_avg experience_avg_sq share_top_authors share_top_phd 3.ireport 4.ireport authored_solo share_female_authors editor_present ------------------------------------------------------------------------------ \| Delta-method \| dy/dx std. err. z P>\|z\| [95% conf. interval] -------------+---------------------------------------------------------------- DID \| -.0363211 .0589632 -0.62 0.538 -.1518869 .0792446 IV \| .094449 .0502584 1.88 0.060 -.0040556 .1929537 RDD \| .0393264 .0731264 0.54 0.591 -.1039988 .1826516 \| year \| 2018 \| . (not estimable) \| unique_j \| 2 \| . (not estimable) 3 \| . (not estimable) 4 \| . (not estimable) 5 \| . (not estimable) 7 \| . (not estimable) 8 \| . (not estimable) 9 \| . (not estimable) 10 \| . (not estimable) 11 \| . (not estimable) 12 \| . (not estimable) 13 \| . (not estimable) 14 \| . (not estimable) 15 \| . (not estimable) 16 \| . (not estimable) 17 \| . (not estimable) 18 \| . (not estimable) 19 \| . (not estimable) 20 \| . (not estimable) 21 \| . (not estimable) 22 \| . (not estimable) 23 \| . (not estimable) 24 \| . (not estimable) 25 \| . (not estimable) \| experience~g \| -.0002103 .0111699 -0.02 0.985 -.0221028 .0216822 experience~q \| -.0043239 .0321318 -0.13 0.893 -.067301 .0586532 share_top_~s \| -.0799536 .0686192 -1.17 0.244 -.2144448 .0545376 share_top_~d \| .1449032 .0613735 2.36 0.018 .0246134 .265193 \| ireport \| 3 \| . (not estimable) 4 \| . (not estimable) \| authored_s~o \| -.0582266 .0634362 -0.92 0.359 -.1825593 .0661061 share_fema~s \| -.0061409 .0580097 -0.11 0.916 -.1198379 .1075561 editor_pre~t \| -.0237157 .058194 -0.41 0.684 -.137774 .0903425 ------------------------------------------------------------------------------ Note: dy/dx for factor levels is the discrete change from the base level. (est6 stored) .
▼	66	estadd local Window "[`threshold'$\pm$0.20]" estadd local Window "[1.96$\pm$0.20]" . estadd local Window "[`threshold'$\pm$0.20]" added macro: e(Window) : "[1.96$\pm$0.20]" .
▼	67	sum `depvar' if t>(`threshold'-0.2) & t<(`threshold'+0.2) & method=="RCT" sum sign_5pct if t>(1.96-0.2) & t<(1.96+0.2) & method=="RCT" . sum `depvar' if t>(`threshold'-0.2) & t<(`threshold'+0.2) > & method=="RCT" Variable \| Obs Mean Std. dev. Min Max -------------+--------------------------------------------------------- sign_5pct \| 501 .4870259 .5003312 0 1 .
▼	68	`estadd local rct_sign = round(r(mean), 0.01)` `. estadd local rct_sign = round(r(mean), 0.01) added macro: e(rct_sign) : ".49" .`
	69
▼	70	`esttab, margin ///` esttab, margin keep(DID IV RDD top5 2018.year experience_avg experience_avg_sq share_top_authors share_top_phd ) label stats(N Window rct_sign, fmt(%9.0fc) labels("Observations" "Window" "RCT sig rate")) . esttab, margin keep(DID IV RDD top5 2018.year experience_a > vg experience_avg_sq share_top_authors share_top_phd ) label stats(N Window r > ct_sign, fmt(%9.0fc) labels("Observations" "Window" "RCT sig rate")) ------------------------------------------------------------------------------- > ------------------------------------- (1) (2) (3) ( > 4) (5) (6) > ------------------------------------------------------------------------------- > ------------------------------------- DID 0.0556 0.0454 0.0292 0.02 > 82 0.0242 -0.0363 (1.45) (1.16) (0.73) (0.6 > 9) (0.54) (-0.62) IV 0.101 0.0998 0.0790* 0.08 > 41* 0.0974* 0.0944 (2.98) (2.72) (2.08) (2.2 > 3) (2.35) (1.88) RDD 0.0939 0.0824 0.0689 0.06 > 89 0.0736 0.0393 (1.48) (1.35) (1.18) (1.1 > 8) (1.22) (0.54) Top 5 -0.0281 -0.0207 > (-0.52) (-0.19) > Year=2018 0.00616 0.0126 0.02 > 17 -0.00399 0 (0.19) (0.38) (0.6 > 3) (-0.11) (.) Experience -0.00760 -0.0134 -0.01 > 32 -0.0105 -0.000210 (-0.92) (-1.58) (-1.5 > 7) (-1.09) (-0.02) Experience squared 0.00227 0.0174 0.01 > 97 0.0197 -0.00432 (0.11) (0.79) (0.9 > 0) (0.76) (-0.13) Top institution -0.00138 0.00266 0.001 > 79 -0.0396 -0.0800 (-0.03) (0.05) (0.0 > 3) (-0.67) (-1.17) Top PhD institution 0.0144 -0.0135 -0.01 > 28 0.0581 0.145* (0.32) (-0.30) (-0.2 > 8) (1.15) (2.36) ------------------------------------------------------------------------------- > ------------------------------------- Observations 3,558 3,558 3,558 3,5 > 58 2,626 1,585 Window [1.96$\pm$0.50] [1.96$\pm$0.50] [1.96$\pm$0.50] [ > 1.96$\pm$0.50] [1.96$\pm$0.35] [1.96$\pm$0.20] RCT sig rate .47 .47 .47 . > 47 .48 .49 ------------------------------------------------------------------------------- > ------------------------------------- Marginal effects; t statistics in parentheses (d) for discrete change of dummy variable from 0 to 1 * p<0.05, p<0.01, * p<0.001 .
	71	`keep(DID IV RDD top5 2018.year experience_avg experience_avg_sq share_top_authors share_top_phd ) label stats(N Window rct_sign, fmt(%9.0fc) labels("Observations" "Window" "RCT sig rate"))`
	72
▼	73	esttab using table_2_caliper_`depvar'.tex, margin /// esttab using table_2_caliper_sign_5pct.tex, margin keep(DID IV RDD top5 2018.year experience_avg experience_avg_sq share_top_authors share_top_phd) label stats(N Window rct_sign, fmt(%9.0fc) labels("Observations" "Window" "RCT sig rate")) mtitles() nomtitles nostar compress se(3) b(3) replace nogaps noomitted indicate( "Reporting Method = ireport" "Solo Authored = authored_solo" "Share Female Authors = share_female_authors" "Editor = editor_present" "Field FE = FINANCE" "Journal FE = unique_j" , labels("Y" " ")) nonotes . esttab using "table_2_caliper_sign_5pct.tex", margin keep(DID IV > RDD top5 2018.year experience_avg experience_avg_sq share_top_authors share_t > op_phd) label stats(N Window rct_sign, fmt(%9.0fc) labels("Observations" "Wi > ndow" "RCT sig rate")) mtitles() nomtitles nostar compress se(3) b(3) replace > nogaps noomitted indicate( "Reporting Method = ireport" "Solo Authored = au > thored_solo" "Share Female Authors = share_female_authors" "Editor = editor_p > resent" "Field FE = FINANCE" "Journal FE = unique_j" , labels("Y" " ")) nono > tes (output written to table_2_caliper_sign_5pct.tex) .
	74	`keep(DID IV RDD top5 2018.year experience_avg experience_avg_sq share_top_authors share_top_phd) label stats(N Window rct_sign, fmt(%9.0fc) labels("Observations" "Window" "RCT sig rate")) ///`
	75	`mtitles() nomtitles nostar ///`
	76	`compress se(3) b(3) replace nogaps noomitted ///`
	77	`indicate( ///`
	78	`"Reporting Method = *ireport" ///`
	79	`"Solo Authored = authored_solo" ///`
	80	`"Share Female Authors = share_female_authors" ///`
	81	`"Editor = editor_present" ///`
	82	`"Field FE = FINANCE" ///`
	83	`"Journal FE = *unique_j" ///`
	84	`, labels("Y" " ")) ///`
	85	`nonotes`
	86
	87
	88
	89	`** Table A5: 5% significance treshold`
	90
	91	`* read in the data`
▼	92	`cd "$dir_data"` `cd "/home/rstudio/repbox/projects_ejd/aer_112_9_9/mod/Scripts/Data" . cd "${repbox_path}/Data" /home/rstudio/repbox/projects_ejd/aer_112_9_9/mod/Data .`
▼	93	`capture use "MM_new.dta", clear` `. capture use "MM_new.dta", clear .`
	94
	95	`* determine folder to store results`
▼	96	`cd "$dir_results"` `cd "/home/rstudio/repbox/projects_ejd/aer_112_9_9/mod/Scripts/Results" . cd "${repbox_path}/Results" /home/rstudio/repbox/projects_ejd/aer_112_9_9/mod/Results .`
	97
	98
	99	`* drop obs with small significand`
▼	100	`keep if keep_obs==1` `. keep if keep_obs==1 (8,233 observations deleted) .`
	101
	102	`* first: 5% threshold`
	103
▼	104	`local depvar "sign_10pct"` `. local depvar "sign_10pct" .`
▼	105	`local threshold 1.65` `. local threshold 1.65 .`
▼	106	`local weight1 "pw="` `. local weight1 "pw=" .`
▼	107	`local weight2 "aw"` `. local weight2 "aw" .`
	108
	109
▼	110	`eststo clear` `. eststo clear .`
	111
▼	112	probit `depvar' DID IV RDD if t>(`threshold'-0.5) & t<(`threshold'+0.5) [`weight1'`weight2'], cluster(journal_article_cluster) probit sign_10pct DID IV RDD if t>(1.65-0.5) & t<(1.65+0.5) [pw=aw], cluster(journal_article_cluster) . probit `depvar' DID IV RDD if t>(`threshold'-0.5) & t<(`th > reshold'+0.5) [`weight1'`weight2'], cluster(journal_article_cluster) Iteration 0: log pseudolikelihood = -658201.09 Iteration 1: log pseudolikelihood = -653009.87 Iteration 2: log pseudolikelihood = -653009.5 Iteration 3: log pseudolikelihood = -653009.5 Probit regression Number of obs = 3,470 Wald chi2(3) = 12.36 Prob > chi2 = 0.0062 Log pseudolikelihood = -653009.5 Pseudo R2 = 0.0079 (Std. err. adjusted for 446 clusters in journal_article_cluster) ------------------------------------------------------------------------------ \| Robust sign_10pct \| Coefficient std. err. z P>\|z\| [95% conf. interval] -------------+---------------------------------------------------------------- DID \| .2674024 .1183662 2.26 0.024 .0354088 .4993959 IV \| .3088297 .0997324 3.10 0.002 .1133578 .5043016 RDD \| .0401727 .1131901 0.35 0.723 -.1816758 .2620213 _cons \| .1222091 .0587997 2.08 0.038 .0069638 .2374544 ------------------------------------------------------------------------------ .
▼	113	`eststo : margins, dydx() post` . eststo : margins, dydx() post Average marginal effects Number of obs = 3,470 Model VCE: Robust Expression: Pr(sign_10pct), predict() dy/dx wrt: DID IV RDD ------------------------------------------------------------------------------ \| Delta-method \| dy/dx std. err. z P>\|z\| [95% conf. interval] -------------+---------------------------------------------------------------- DID \| .1001962 .0435242 2.30 0.021 .0148903 .185502 IV \| .115719 .0361463 3.20 0.001 .0448736 .1865645 RDD \| .0150528 .0424067 0.35 0.723 -.0680628 .0981684 ------------------------------------------------------------------------------ (est1 stored) .
▼	114	estadd local Window "[`threshold'$\pm$0.50]" estadd local Window "[1.65$\pm$0.50]" . estadd local Window "[`threshold'$\pm$0.50]" added macro: e(Window) : "[1.65$\pm$0.50]" .
▼	115	sum `depvar' if t>(`threshold'-0.5) & t<(`threshold'+0.5) & method=="RCT" sum sign_10pct if t>(1.65-0.5) & t<(1.65+0.5) & method=="RCT" . sum `depvar' if t>(`threshold'-0.5) & t<(`threshold'+0.5) > & method=="RCT" Variable \| Obs Mean Std. dev. Min Max -------------+--------------------------------------------------------- sign_10pct \| 1,216 .5164474 .499935 0 1 .
▼	116	`estadd local rct_sign = round(r(mean), 0.01)` `. estadd local rct_sign = round(r(mean), 0.01) added macro: e(rct_sign) : ".52" .`
	117
▼	118	probit `depvar' DID IV RDD top5 i.year experience_avg experience_avg_sq share_top_authors share_top_phd i.ireport authored_solo share_female_authors editor_present if t>(`threshold'-0.5) & t<(`threshold'+0.5) [`weight1'`weight2'], cluster(journal_article_cluster) probit sign_10pct DID IV RDD top5 i.year experience_avg experience_avg_sq share_top_authors share_top_phd i.ireport authored_solo share_female_authors editor_present if t>(1.65-0.5) & t<(1.65+0.5) [pw=aw], cluster(journal_article_cluster) . probit `depvar' DID IV RDD top5 i.year experience_avg expe > rience_avg_sq share_top_authors share_top_phd i.ireport authored_solo share_f > emale_authors editor_present if t>(`threshold'-0.5) & t<(`threshold'+0.5) [`w > eight1'`weight2'], cluster(journal_article_cluster) Iteration 0: log pseudolikelihood = -658201.09 Iteration 1: log pseudolikelihood = -646729.81 Iteration 2: log pseudolikelihood = -646713.3 Iteration 3: log pseudolikelihood = -646713.29 Probit regression Number of obs = 3,470 Wald chi2(15) = 24.53 Prob > chi2 = 0.0566 Log pseudolikelihood = -646713.29 Pseudo R2 = 0.0175 (Std. err. adjusted for 446 clusters in journal_article_cluster) ------------------------------------------------------------------------------ \| Robust sign_10pct \| Coefficient std. err. z P>\|z\| [95% conf. interval] -------------+---------------------------------------------------------------- DID \| .3054278 .1103157 2.77 0.006 .0892129 .5216426 IV \| .340464 .1044438 3.26 0.001 .1357579 .5451702 RDD \| .0232021 .1105085 0.21 0.834 -.1933906 .2397947 top5 \| .1614665 .1314808 1.23 0.219 -.0962312 .4191643 \| year \| 2018 \| .0084053 .0934317 0.09 0.928 -.1747174 .191528 \| experience~g \| -.0049399 .0238661 -0.21 0.836 -.0517165 .0418367 experience~q \| -.0087031 .0724233 -0.12 0.904 -.1506502 .1332441 share_top_~s \| -.154885 .1321336 -1.17 0.241 -.413862 .104092 share_top_~d \| -.043656 .1226124 -0.36 0.722 -.2839718 .1966599 \| ireport \| 2 \| -.3662434 .7540036 -0.49 0.627 -1.844063 1.111577 3 \| -.5069767 .7335503 -0.69 0.489 -1.944709 .9307555 4 \| -.7354124 .757664 -0.97 0.332 -2.220407 .7495818 \| authored_s~o \| .0978376 .1332095 0.73 0.463 -.1632481 .3589233 share_fema~s \| .1324691 .1483577 0.89 0.372 -.1583066 .4232448 editor_pre~t \| .0293531 .125409 0.23 0.815 -.2164439 .2751501 _cons \| .6414197 .7700302 0.83 0.405 -.8678117 2.150651 ------------------------------------------------------------------------------ .
▼	119	`eststo : margins, dydx() post` . eststo : margins, dydx() post Average marginal effects Number of obs = 3,470 Model VCE: Robust Expression: Pr(sign_10pct), predict() dy/dx wrt: DID IV RDD top5 2018.year experience_avg experience_avg_sq share_top_authors share_top_phd 2.ireport 3.ireport 4.ireport authored_solo share_female_authors editor_present ------------------------------------------------------------------------------ \| Delta-method \| dy/dx std. err. z P>\|z\| [95% conf. interval] -------------+---------------------------------------------------------------- DID \| .1132788 .0401968 2.82 0.005 .0344945 .1920632 IV \| .1262733 .0375258 3.36 0.001 .0527242 .1998224 RDD \| .0086053 .0409854 0.21 0.834 -.0717246 .0889352 top5 \| .0598857 .048525 1.23 0.217 -.0352215 .1549928 \| year \| 2018 \| .0031182 .0346647 0.09 0.928 -.0648232 .0710597 \| experience~g \| -.0018321 .0088484 -0.21 0.836 -.0191746 .0155104 experience~q \| -.0032278 .0268643 -0.12 0.904 -.0558809 .0494252 share_top_~s \| -.0574446 .0487798 -1.18 0.239 -.1530512 .0381619 share_top_~d \| -.0161914 .0454562 -0.36 0.722 -.1052839 .0729012 \| ireport \| 2 \| -.1152325 .2114157 -0.55 0.586 -.5295997 .2991347 3 \| -.1659906 .2026644 -0.82 0.413 -.5632055 .2312242 4 \| -.2532284 .2159417 -1.17 0.241 -.6764663 .1700094 \| authored_s~o \| .0362866 .0493765 0.73 0.462 -.0604895 .1330627 share_fema~s \| .0491309 .0549052 0.89 0.371 -.0584813 .1567432 editor_pre~t \| .0108866 .0464877 0.23 0.815 -.0802276 .1020008 ------------------------------------------------------------------------------ Note: dy/dx for factor levels is the discrete change from the base level. (est2 stored) .
▼	120	estadd local Window "[`threshold'$\pm$0.50]" estadd local Window "[1.65$\pm$0.50]" . estadd local Window "[`threshold'$\pm$0.50]" added macro: e(Window) : "[1.65$\pm$0.50]" .
▼	121	sum `depvar' if t>(`threshold'-0.5) & t<(`threshold'+0.5) & method=="RCT" sum sign_10pct if t>(1.65-0.5) & t<(1.65+0.5) & method=="RCT" . sum `depvar' if t>(`threshold'-0.5) & t<(`threshold'+0.5) > & method=="RCT" Variable \| Obs Mean Std. dev. Min Max -------------+--------------------------------------------------------- sign_10pct \| 1,216 .5164474 .499935 0 1 .
▼	122	`estadd local rct_sign = round(r(mean), 0.01)` `. estadd local rct_sign = round(r(mean), 0.01) added macro: e(rct_sign) : ".52" .`
	123
▼	124	probit `depvar' DID IV RDD top5 i.year FINANCE MACRO_GROWTH GEN_INT EXP DEV LABOR PUB URB experience_avg experience_avg_sq share_top_authors share_top_phd i.ireport authored_solo share_female_authors editor_present if t>(`threshold'-0.5) & t<(`threshold'+0.5) [`weight1'`weight2'], cluster(journal_article_cluster) probit sign_10pct DID IV RDD top5 i.year FINANCE MACRO_GROWTH GEN_INT EXP DEV LABOR PUB URB experience_avg experience_avg_sq share_top_authors share_top_phd i.ireport authored_solo share_female_authors editor_present if t>(1.65-0.5) & t<(1.65+0.5) [pw=aw], cluster(journal_article_cluster) . probit `depvar' DID IV RDD top5 i.year FINANCE MACRO_GROWT > H GEN_INT EXP DEV LABOR PUB URB experience_avg experience_avg_sq share_top_au > thors share_top_phd i.ireport authored_solo share_female_authors editor_prese > nt if t>(`threshold'-0.5) & t<(`threshold'+0.5) [`weight1'`weight2'], cluster > (journal_article_cluster) Iteration 0: log pseudolikelihood = -658201.09 Iteration 1: log pseudolikelihood = -640456.59 Iteration 2: log pseudolikelihood = -640307.62 Iteration 3: log pseudolikelihood = -640306.84 Iteration 4: log pseudolikelihood = -640306.84 Probit regression Number of obs = 3,470 Wald chi2(23) = 43.62 Prob > chi2 = 0.0058 Log pseudolikelihood = -640306.84 Pseudo R2 = 0.0272 (Std. err. adjusted for 446 clusters in journal_article_cluster) ------------------------------------------------------------------------------ \| Robust sign_10pct \| Coefficient std. err. z P>\|z\| [95% conf. interval] -------------+---------------------------------------------------------------- DID \| .2942549 .1133104 2.60 0.009 .0721707 .5163391 IV \| .2744547 .1118847 2.45 0.014 .0551647 .4937447 RDD \| .0122454 .1194844 0.10 0.918 -.2219398 .2464306 top5 \| -.1289498 .2771565 -0.47 0.642 -.6721665 .4142669 \| year \| 2018 \| .0278961 .0924776 0.30 0.763 -.1533567 .2091489 \| FINANCE \| -.1095336 .2731278 -0.40 0.688 -.6448544 .4257871 MACRO_GROWTH \| .3437249 .5542687 0.62 0.535 -.7426217 1.430072 GEN_INT \| -.2988225 .2516392 -1.19 0.235 -.7920262 .1943812 EXP \| .9774686 .5401224 1.81 0.070 -.0811518 2.036089 DEV \| -.410228 .2848745 -1.44 0.150 -.9685718 .1481158 LABOR \| -.2500453 .3250758 -0.77 0.442 -.8871821 .3870915 PUB \| -.3855273 .2648781 -1.46 0.146 -.9046789 .1336242 URB \| -.5564295 .2934216 -1.90 0.058 -1.131525 .0186662 experience~g \| -.0150776 .0233984 -0.64 0.519 -.0609377 .0307825 experience~q \| .0214136 .0705808 0.30 0.762 -.1169223 .1597496 share_top_~s \| -.120671 .1339409 -0.90 0.368 -.3831903 .1418482 share_top_~d \| -.0882738 .1217286 -0.73 0.468 -.3268574 .1503098 \| ireport \| 2 \| -.4416945 .7565664 -0.58 0.559 -1.924537 1.041148 3 \| -.5465874 .7397134 -0.74 0.460 -1.996399 .9032242 4 \| -.9035389 .7719247 -1.17 0.242 -2.416483 .6094056 \| authored_s~o \| .0506023 .1361734 0.37 0.710 -.2162927 .3174973 share_fema~s \| .125262 .1374177 0.91 0.362 -.1440718 .3945958 editor_pre~t \| .0017211 .1270381 0.01 0.989 -.2472689 .2507112 _cons \| 1.100199 .8282919 1.33 0.184 -.5232229 2.723622 ------------------------------------------------------------------------------ .
▼	125	`eststo : margins, dydx() post` . eststo : margins, dydx() post Average marginal effects Number of obs = 3,470 Model VCE: Robust Expression: Pr(sign_10pct), predict() dy/dx wrt: DID IV RDD top5 2018.year FINANCE MACRO_GROWTH GEN_INT EXP DEV LABOR PUB URB experience_avg experience_avg_sq share_top_authors share_top_phd 2.ireport 3.ireport 4.ireport authored_solo share_female_authors editor_present ------------------------------------------------------------------------------ \| Delta-method \| dy/dx std. err. z P>\|z\| [95% conf. interval] -------------+---------------------------------------------------------------- DID \| .1080061 .041033 2.63 0.008 .0275828 .1884294 IV \| .1007385 .0401824 2.51 0.012 .0219824 .1794946 RDD \| .0044947 .0438523 0.10 0.918 -.0814542 .0904435 top5 \| -.047331 .1018554 -0.46 0.642 -.246964 .152302 \| year \| 2018 \| .0102479 .0339954 0.30 0.763 -.0563819 .0768777 \| FINANCE \| -.0402043 .1003217 -0.40 0.689 -.2368311 .1564226 MACRO_GROWTH \| .1261641 .2031288 0.62 0.535 -.271961 .5242891 GEN_INT \| -.1096827 .0924311 -1.19 0.235 -.2908443 .071479 EXP \| .3587794 .198456 1.81 0.071 -.0301873 .747746 DEV \| -.150574 .1047323 -1.44 0.151 -.3558456 .0546976 LABOR \| -.091779 .1193533 -0.77 0.442 -.3257071 .1421491 PUB \| -.1415076 .0972772 -1.45 0.146 -.3321674 .0491522 URB \| -.2042372 .1074175 -1.90 0.057 -.4147717 .0062973 experience~g \| -.0055342 .0085814 -0.64 0.519 -.0223534 .0112849 experience~q \| .0078599 .0259021 0.30 0.762 -.0429074 .0586271 share_top_~s \| -.0442922 .0490166 -0.90 0.366 -.140363 .0517786 share_top_~d \| -.0324008 .0446365 -0.73 0.468 -.1198867 .055085 \| ireport \| 2 \| -.1360979 .2015814 -0.68 0.500 -.5311902 .2589944 3 \| -.1735551 .194067 -0.89 0.371 -.5539195 .2068093 4 \| -.3091124 .2109962 -1.47 0.143 -.7226574 .1044325 \| authored_s~o \| .0185736 .0499735 0.37 0.710 -.0793726 .1165198 share_fema~s \| .0459774 .0504 0.91 0.362 -.0528048 .1447595 editor_pre~t \| .0006317 .0466283 0.01 0.989 -.0907581 .0920216 ------------------------------------------------------------------------------ Note: dy/dx for factor levels is the discrete change from the base level. (est3 stored) .
▼	126	estadd local Window "[`threshold'$\pm$0.50]" estadd local Window "[1.65$\pm$0.50]" . estadd local Window "[`threshold'$\pm$0.50]" added macro: e(Window) : "[1.65$\pm$0.50]" .
▼	127	sum `depvar' if t>(`threshold'-0.5) & t<(`threshold'+0.5) & method=="RCT" sum sign_10pct if t>(1.65-0.5) & t<(1.65+0.5) & method=="RCT" . sum `depvar' if t>(`threshold'-0.5) & t<(`threshold'+0.5) > & method=="RCT" Variable \| Obs Mean Std. dev. Min Max -------------+--------------------------------------------------------- sign_10pct \| 1,216 .5164474 .499935 0 1 .
▼	128	`estadd local rct_sign = round(r(mean), 0.01)` `. estadd local rct_sign = round(r(mean), 0.01) added macro: e(rct_sign) : ".52" .`
	129
▼	130	probit `depvar' DID IV RDD i.year i.unique_j experience_avg experience_avg_sq share_top_authors share_top_phd i.ireport authored_solo share_female_authors editor_present if t>(`threshold'-0.5) & t<(`threshold'+0.5) [`weight1'`weight2'], cluster(journal_article_cluster) probit sign_10pct DID IV RDD i.year i.unique_j experience_avg experience_avg_sq share_top_authors share_top_phd i.ireport authored_solo share_female_authors editor_present if t>(1.65-0.5) & t<(1.65+0.5) [pw=aw], cluster(journal_article_cluster) . probit `depvar' DID IV RDD i.year i.unique_j experience_av > g experience_avg_sq share_top_authors share_top_phd i.ireport authored_solo s > hare_female_authors editor_present if t>(`threshold'-0.5) & t<(`threshold'+0. > 5) [`weight1'`weight2'], cluster(journal_article_cluster) note: 6.unique_j != 0 predicts failure perfectly; 6.unique_j omitted and 1 obs not used. Iteration 0: log pseudolikelihood = -657374.36 Iteration 1: log pseudolikelihood = -629017.21 Iteration 2: log pseudolikelihood = -628721.33 Iteration 3: log pseudolikelihood = -628720.44 Iteration 4: log pseudolikelihood = -628720.44 Probit regression Number of obs = 3,469 Wald chi2(37) = 75.75 Prob > chi2 = 0.0002 Log pseudolikelihood = -628720.44 Pseudo R2 = 0.0436 (Std. err. adjusted for 445 clusters in journal_article_cluster) ------------------------------------------------------------------------------ \| Robust sign_10pct \| Coefficient std. err. z P>\|z\| [95% conf. interval] -------------+---------------------------------------------------------------- DID \| .3067344 .1165659 2.63 0.009 .0782694 .5351995 IV \| .3094702 .1156761 2.68 0.007 .0827491 .5361912 RDD \| .0141679 .124399 0.11 0.909 -.2296496 .2579855 \| year \| 2018 \| .0545419 .0956883 0.57 0.569 -.1330038 .2420876 \| unique_j \| 2 \| -.3307762 .3816209 -0.87 0.386 -1.078739 .417187 3 \| .0219097 .3516636 0.06 0.950 -.6673382 .7111576 4 \| -.027792 .2757375 -0.10 0.920 -.5682277 .5126436 5 \| -.268534 .3742118 -0.72 0.473 -1.001976 .4649077 7 \| .5594341 .6126629 0.91 0.361 -.6413631 1.760231 8 \| -.3459349 .2533849 -1.37 0.172 -.8425602 .1506904 9 \| -.1214621 .2733101 -0.44 0.657 -.6571401 .4142159 10 \| .3881216 .3654681 1.06 0.288 -.3281827 1.104426 11 \| -.2545579 .2253984 -1.13 0.259 -.6963307 .1872149 12 \| .0324593 .2896925 0.11 0.911 -.5353276 .6002462 13 \| -.3054428 .2736658 -1.12 0.264 -.8418178 .2309323 14 \| -.0343718 .3058782 -0.11 0.911 -.633882 .5651384 15 \| -.6641387 .2789404 -2.38 0.017 -1.210852 -.1174255 16 \| .0130772 .2929312 0.04 0.964 -.5610574 .5872117 17 \| .9674764 .525976 1.84 0.066 -.0634176 1.99837 18 \| -.4258668 .2305086 -1.85 0.065 -.8776553 .0259217 19 \| -.2479698 .2987351 -0.83 0.407 -.8334798 .3375402 20 \| .601708 .3685704 1.63 0.103 -.1206767 1.324093 21 \| .6619555 .940323 0.70 0.481 -1.181044 2.504955 22 \| -.4065839 .268071 -1.52 0.129 -.9319934 .1188256 23 \| -.0403292 .2361529 -0.17 0.864 -.5031804 .422522 24 \| -.5686039 .254211 -2.24 0.025 -1.066848 -.0703595 25 \| -.4890831 .2333259 -2.10 0.036 -.9463934 -.0317727 \| experience~g \| -.0182684 .0228858 -0.80 0.425 -.0631238 .0265871 experience~q \| .0242088 .0671281 0.36 0.718 -.1073599 .1557775 share_top_~s \| -.1080948 .1346331 -0.80 0.422 -.3719709 .1557813 share_top_~d \| -.1238134 .1205535 -1.03 0.304 -.3600939 .112467 \| ireport \| 2 \| .2282544 .861652 0.26 0.791 -1.460552 1.917061 3 \| .1490447 .8503858 0.18 0.861 -1.517681 1.81577 4 \| -.2435608 .8794555 -0.28 0.782 -1.967262 1.48014 \| authored_s~o \| .0647148 .1372601 0.47 0.637 -.2043102 .3337397 share_fema~s \| .1430325 .1369329 1.04 0.296 -.1253511 .4114161 editor_pre~t \| .0236931 .1276777 0.19 0.853 -.2265505 .2739367 _cons \| .398202 .8670902 0.46 0.646 -1.301263 2.097667 ------------------------------------------------------------------------------ .
▼	131	`eststo : margins, dydx() post` . eststo : margins, dydx() post Average marginal effects Number of obs = 3,469 Model VCE: Robust Expression: Pr(sign_10pct), predict() dy/dx wrt: DID IV RDD 2018.year 2.unique_j 3.unique_j 4.unique_j 5.unique_j 7.unique_j 8.unique_j 9.unique_j 10.unique_j 11.unique_j 12.unique_j 13.unique_j 14.unique_j 15.unique_j 16.unique_j 17.unique_j 18.unique_j 19.unique_j 20.unique_j 21.unique_j 22.unique_j 23.unique_j 24.unique_j 25.unique_j experience_avg experience_avg_sq share_top_authors share_top_phd 2.ireport 3.ireport 4.ireport authored_solo share_female_authors editor_present ------------------------------------------------------------------------------ \| Delta-method \| dy/dx std. err. z P>\|z\| [95% conf. interval] -------------+---------------------------------------------------------------- DID \| .1105029 .0414564 2.67 0.008 .0292499 .1917559 IV \| .1114885 .0407369 2.74 0.006 .0316456 .1913313 RDD \| .0051041 .0448056 0.11 0.909 -.0827133 .0929215 \| year \| 2018 \| .0196757 .0345658 0.57 0.569 -.0480721 .0874236 \| unique_j \| 2 \| -.1179246 .1403233 -0.84 0.401 -.3929533 .1571041 3 \| .0071871 .1150011 0.06 0.950 -.218211 .2325852 4 \| -.0092454 .0917467 -0.10 0.920 -.1890658 .1705749 5 \| -.0946056 .135259 -0.70 0.484 -.3597084 .1704971 7 \| .1513191 .1368665 1.11 0.269 -.1169344 .4195725 8 \| -.1236623 .0894426 -1.38 0.167 -.2989666 .051642 9 \| -.0414059 .0933564 -0.44 0.657 -.2243811 .1415693 10 \| .1124645 .0997144 1.13 0.259 -.0829721 .3079012 11 \| -.0894279 .0772883 -1.16 0.247 -.2409102 .0620544 12 \| .010615 .0946358 0.11 0.911 -.1748678 .1960979 13 \| -.1083848 .0966677 -1.12 0.262 -.2978501 .0810805 14 \| -.0114549 .102104 -0.11 0.911 -.2115751 .1886652 15 \| -.2469285 .1007434 -2.45 0.014 -.4443819 -.049475 16 \| .0043007 .0963072 0.04 0.964 -.1844579 .1930592 17 \| .2178429 .0867576 2.51 0.012 .0478012 .3878847 18 \| -.154228 .0806022 -1.91 0.056 -.3122053 .0037494 19 \| -.0869952 .1056579 -0.82 0.410 -.2940809 .1200904 20 \| .1598717 .0889608 1.80 0.072 -.0144884 .3342317 21 \| .1713664 .1784299 0.96 0.337 -.1783498 .5210827 22 \| -.1468116 .0959282 -1.53 0.126 -.3348274 .0412042 23 \| -.0134621 .0785457 -0.17 0.864 -.167409 .1404847 24 \| -.2096611 .0909498 -2.31 0.021 -.3879193 -.0314028 25 \| -.1786875 .0820988 -2.18 0.030 -.3395982 -.0177768 \| experience~g \| -.0065813 .0082354 -0.80 0.424 -.0227224 .0095598 experience~q \| .0087214 .0241772 0.36 0.718 -.0386652 .0561079 share_top_~s \| -.0389418 .0483934 -0.80 0.421 -.133791 .0559074 share_top_~d \| -.0446045 .0433913 -1.03 0.304 -.1296499 .0404409 \| ireport \| 2 \| .0819634 .3183557 0.26 0.797 -.5420022 .705929 3 \| .0541999 .3148587 0.17 0.863 -.5629119 .6713116 4 \| -.0917247 .3265767 -0.28 0.779 -.7318034 .5483539 \| authored_s~o \| .0233139 .0494329 0.47 0.637 -.0735729 .1202007 share_fema~s \| .0515283 .0492539 1.05 0.295 -.0450075 .1480641 editor_pre~t \| .0085356 .0459791 0.19 0.853 -.0815819 .098653 ------------------------------------------------------------------------------ Note: dy/dx for factor levels is the discrete change from the base level. (est4 stored) .
▼	132	estadd local Window "[`threshold'$\pm$0.50]" estadd local Window "[1.65$\pm$0.50]" . estadd local Window "[`threshold'$\pm$0.50]" added macro: e(Window) : "[1.65$\pm$0.50]" .
▼	133	sum `depvar' if t>(`threshold'-0.5) & t<(`threshold'+0.5) & method=="RCT" sum sign_10pct if t>(1.65-0.5) & t<(1.65+0.5) & method=="RCT" . sum `depvar' if t>(`threshold'-0.5) & t<(`threshold'+0.5) > & method=="RCT" Variable \| Obs Mean Std. dev. Min Max -------------+--------------------------------------------------------- sign_10pct \| 1,216 .5164474 .499935 0 1 .
▼	134	`estadd local rct_sign = round(r(mean), 0.01)` `. estadd local rct_sign = round(r(mean), 0.01) added macro: e(rct_sign) : ".52" .`
	135
▼	136	probit `depvar' DID IV RDD i.year i.unique_j experience_avg experience_avg_sq share_top_authors share_top_phd i.ireport authored_solo share_female_authors editor_present if t>(`threshold'-0.35) & t<(`threshold'+0.35) [`weight1'`weight2'], cluster(journal_article_cluster) probit sign_10pct DID IV RDD i.year i.unique_j experience_avg experience_avg_sq share_top_authors share_top_phd i.ireport authored_solo share_female_authors editor_present if t>(1.65-0.35) & t<(1.65+0.35) [pw=aw], cluster(journal_article_cluster) . probit `depvar' DID IV RDD i.year i.unique_j experience_av > g experience_avg_sq share_top_authors share_top_phd i.ireport authored_solo s > hare_female_authors editor_present if t>(`threshold'-0.35) & t<(`threshold'+0 > .35) [`weight1'`weight2'], cluster(journal_article_cluster) note: 6.unique_j != 0 predicts failure perfectly; 6.unique_j omitted and 1 obs not used. Iteration 0: log pseudolikelihood = -442242.94 Iteration 1: log pseudolikelihood = -419798.28 Iteration 2: log pseudolikelihood = -419521.18 Iteration 3: log pseudolikelihood = -419520.09 Iteration 4: log pseudolikelihood = -419520.09 Probit regression Number of obs = 2,377 Wald chi2(37) = 73.56 Prob > chi2 = 0.0003 Log pseudolikelihood = -419520.09 Pseudo R2 = 0.0514 (Std. err. adjusted for 413 clusters in journal_article_cluster) ------------------------------------------------------------------------------ \| Robust sign_10pct \| Coefficient std. err. z P>\|z\| [95% conf. interval] -------------+---------------------------------------------------------------- DID \| .2845893 .1320785 2.15 0.031 .0257202 .5434584 IV \| .1813196 .1183084 1.53 0.125 -.0505606 .4131997 RDD \| -.0659786 .1537339 -0.43 0.668 -.3672915 .2353343 \| year \| 2018 \| .0655507 .1013908 0.65 0.518 -.1331717 .2642731 \| unique_j \| 2 \| -.3064238 .3553262 -0.86 0.388 -1.00285 .3900027 3 \| -.1776791 .296197 -0.60 0.549 -.7582146 .4028565 4 \| .3306152 .3077883 1.07 0.283 -.2726388 .9338692 5 \| .2399634 .3200833 0.75 0.453 -.3873883 .8673151 7 \| .326602 .5400965 0.60 0.545 -.7319678 1.385172 8 \| -.1492463 .2678324 -0.56 0.577 -.6741881 .3756956 9 \| -.0330916 .2461022 -0.13 0.893 -.515443 .4492597 10 \| .9365125 .4985731 1.88 0.060 -.0406728 1.913698 11 \| -.0711041 .228183 -0.31 0.755 -.5183345 .3761263 12 \| -.031446 .3248993 -0.10 0.923 -.6682368 .6053448 13 \| -.2473589 .2865312 -0.86 0.388 -.8089497 .3142319 14 \| .0302252 .3637233 0.08 0.934 -.6826593 .7431098 15 \| -.6346342 .2836079 -2.24 0.025 -1.190496 -.0787729 16 \| .3910687 .3206352 1.22 0.223 -.2373649 1.019502 17 \| 1.104191 .5536038 1.99 0.046 .0191477 2.189235 18 \| -.4406852 .242953 -1.81 0.070 -.9168644 .035494 19 \| -.175174 .2868864 -0.61 0.541 -.737461 .3871131 20 \| 1.107661 .3902658 2.84 0.005 .3427538 1.872567 21 \| .1031202 .7545757 0.14 0.891 -1.375821 1.582061 22 \| -.1074449 .3105217 -0.35 0.729 -.7160564 .5011665 23 \| .1275117 .2587629 0.49 0.622 -.3796542 .6346776 24 \| -.402911 .2785259 -1.45 0.148 -.9488118 .1429898 25 \| -.3036968 .2574991 -1.18 0.238 -.8083858 .2009922 \| experience~g \| -.0426977 .021873 -1.95 0.051 -.0855681 .0001726 experience~q \| .0873579 .0644875 1.35 0.176 -.0390353 .2137511 share_top_~s \| -.0162223 .1422882 -0.11 0.909 -.295102 .2626574 share_top_~d \| -.1635343 .1350543 -1.21 0.226 -.4282359 .1011674 \| ireport \| 2 \| -.3889376 .7540907 -0.52 0.606 -1.866928 1.089053 3 \| -.3847109 .7420405 -0.52 0.604 -1.839084 1.069662 4 \| -.7913694 .7810919 -1.01 0.311 -2.322281 .7395427 \| authored_s~o \| .0360235 .1480467 0.24 0.808 -.2541426 .3261896 share_fema~s \| .2660892 .1530786 1.74 0.082 -.0339394 .5661178 editor_pre~t \| .0597911 .1333152 0.45 0.654 -.201502 .3210841 _cons \| .9238401 .7695609 1.20 0.230 -.5844716 2.432152 ------------------------------------------------------------------------------ .
▼	137	`eststo : margins, dydx() post` . eststo : margins, dydx() post Average marginal effects Number of obs = 2,377 Model VCE: Robust Expression: Pr(sign_10pct), predict() dy/dx wrt: DID IV RDD 2018.year 2.unique_j 3.unique_j 4.unique_j 5.unique_j 7.unique_j 8.unique_j 9.unique_j 10.unique_j 11.unique_j 12.unique_j 13.unique_j 14.unique_j 15.unique_j 16.unique_j 17.unique_j 18.unique_j 19.unique_j 20.unique_j 21.unique_j 22.unique_j 23.unique_j 24.unique_j 25.unique_j experience_avg experience_avg_sq share_top_authors share_top_phd 2.ireport 3.ireport 4.ireport authored_solo share_female_authors editor_present ------------------------------------------------------------------------------ \| Delta-method \| dy/dx std. err. z P>\|z\| [95% conf. interval] -------------+---------------------------------------------------------------- DID \| .1034587 .0474987 2.18 0.029 .0103629 .1965545 IV \| .0659163 .042702 1.54 0.123 -.017778 .1496107 RDD \| -.0239856 .0558904 -0.43 0.668 -.1335288 .0855575 \| year \| 2018 \| .0238433 .0369025 0.65 0.518 -.0484843 .0961709 \| unique_j \| 2 \| -.1153011 .1350907 -0.85 0.393 -.3800741 .1494718 3 \| -.0658718 .1103924 -0.60 0.551 -.2822369 .1504933 4 \| .1100003 .100454 1.10 0.274 -.0868859 .3068865 5 \| .0818409 .1070803 0.76 0.445 -.1280326 .2917144 7 \| .1087893 .1680519 0.65 0.517 -.2205863 .4381649 8 \| -.0551105 .0987842 -0.56 0.577 -.248724 .1385031 9 \| -.0119902 .089054 -0.13 0.893 -.1865328 .1625524 10 \| .251628 .1041688 2.42 0.016 .0474609 .4557951 11 \| -.0259355 .0827795 -0.31 0.754 -.1881804 .1363093 12 \| -.0113906 .1178705 -0.10 0.923 -.2424124 .2196313 13 \| -.0925052 .1068431 -0.87 0.387 -.3019138 .1169035 14 \| .0108202 .129917 0.08 0.934 -.2438124 .2654529 15 \| -.2421215 .1046443 -2.31 0.021 -.4472205 -.0370225 16 \| .1278294 .1022588 1.25 0.211 -.0725942 .328253 17 \| .2766271 .0979856 2.82 0.005 .0845788 .4686754 18 \| -.1674576 .0897594 -1.87 0.062 -.3433828 .0084675 19 \| -.0649209 .106382 -0.61 0.542 -.2734257 .1435839 20 \| .2770859 .0844697 3.28 0.001 .1115285 .4426434 21 \| .0363519 .2605529 0.14 0.889 -.4743223 .5470262 22 \| -.0394247 .1143492 -0.34 0.730 -.263545 .1846956 23 \| .0447039 .0910096 0.49 0.623 -.1336716 .2230794 24 \| -.1527707 .1044384 -1.46 0.144 -.3574662 .0519248 25 \| -.1142454 .0956978 -1.19 0.233 -.3018097 .0733189 \| experience~g \| -.0155222 .007917 -1.96 0.050 -.0310393 -5.11e-06 experience~q \| .0317578 .0233854 1.36 0.174 -.0140768 .0775924 share_top_~s \| -.0058974 .0517172 -0.11 0.909 -.1072613 .0954665 share_top_~d \| -.0594507 .0491035 -1.21 0.226 -.1556918 .0367904 \| ireport \| 2 \| -.129471 .2284283 -0.57 0.571 -.5771822 .3182402 3 \| -.1279519 .2232618 -0.57 0.567 -.565537 .3096332 4 \| -.279108 .2401934 -1.16 0.245 -.7498784 .1916625 \| authored_s~o \| .0130959 .053803 0.24 0.808 -.0923561 .1185478 share_fema~s \| .0967332 .0554889 1.74 0.081 -.0120229 .2054894 editor_pre~t \| .0217363 .0484371 0.45 0.654 -.0731987 .1166712 ------------------------------------------------------------------------------ Note: dy/dx for factor levels is the discrete change from the base level. (est5 stored) .
▼	138	estadd local Window "[`threshold'$\pm$0.35]" estadd local Window "[1.65$\pm$0.35]" . estadd local Window "[`threshold'$\pm$0.35]" added macro: e(Window) : "[1.65$\pm$0.35]" .
▼	139	sum `depvar' if t>(`threshold'-0.35) & t<(`threshold'+0.35) & method=="RCT" sum sign_10pct if t>(1.65-0.35) & t<(1.65+0.35) & method=="RCT" . sum `depvar' if t>(`threshold'-0.35) & t<(`threshold'+0.35 > ) & method=="RCT" Variable \| Obs Mean Std. dev. Min Max -------------+--------------------------------------------------------- sign_10pct \| 823 .5261239 .4996207 0 1 .
▼	140	`estadd local rct_sign = round(r(mean), 0.01)` `. estadd local rct_sign = round(r(mean), 0.01) added macro: e(rct_sign) : ".53" .`
	141
▼	142	probit `depvar' DID IV RDD i.year i.unique_j experience_avg experience_avg_sq share_top_authors share_top_phd i.ireport authored_solo share_female_authors editor_present if t>(`threshold'-0.2) & t<(`threshold'+0.2) [`weight1'`weight2'], cluster(journal_article_cluster) probit sign_10pct DID IV RDD i.year i.unique_j experience_avg experience_avg_sq share_top_authors share_top_phd i.ireport authored_solo share_female_authors editor_present if t>(1.65-0.2) & t<(1.65+0.2) [pw=aw], cluster(journal_article_cluster) . probit `depvar' DID IV RDD i.year i.unique_j experience_av > g experience_avg_sq share_top_authors share_top_phd i.ireport authored_solo s > hare_female_authors editor_present if t>(`threshold'-0.2) & t<(`threshold'+0. > 2) [`weight1'`weight2'], cluster(journal_article_cluster) note: 6.unique_j != 0 predicts failure perfectly; 6.unique_j omitted and 1 obs not used. note: 17.unique_j != 0 predicts success perfectly; 17.unique_j omitted and 2 obs not used. note: 1.ireport != 0 predicts success perfectly; 1.ireport omitted and 2 obs not used. note: 4.ireport omitted because of collinearity. Iteration 0: log pseudolikelihood = -255287.43 Iteration 1: log pseudolikelihood = -238015.26 Iteration 2: log pseudolikelihood = -237925.37 Iteration 3: log pseudolikelihood = -237925.33 Iteration 4: log pseudolikelihood = -237925.33 Probit regression Number of obs = 1,363 Wald chi2(34) = 63.92 Prob > chi2 = 0.0014 Log pseudolikelihood = -237925.33 Pseudo R2 = 0.0680 (Std. err. adjusted for 352 clusters in journal_article_cluster) ------------------------------------------------------------------------------ \| Robust sign_10pct \| Coefficient std. err. z P>\|z\| [95% conf. interval] -------------+---------------------------------------------------------------- DID \| .246094 .1684007 1.46 0.144 -.0839653 .5761534 IV \| .0568339 .1503284 0.38 0.705 -.2378044 .3514722 RDD \| -.2245795 .175924 -1.28 0.202 -.5693841 .1202251 \| year \| 2018 \| .2549064 .1168868 2.18 0.029 .0258124 .4840003 \| unique_j \| 2 \| -.282745 .5654319 -0.50 0.617 -1.390971 .8254811 3 \| -.5659022 .5163728 -1.10 0.273 -1.577974 .44617 4 \| .627347 .3888874 1.61 0.107 -.1348582 1.389552 5 \| .4721226 .488829 0.97 0.334 -.4859647 1.43021 7 \| .0798365 .629183 0.13 0.899 -1.15334 1.313012 8 \| -.2707945 .3183011 -0.85 0.395 -.8946533 .3530642 9 \| .1015442 .3452403 0.29 0.769 -.5751144 .7782028 10 \| .6397329 .4441426 1.44 0.150 -.2307707 1.510236 11 \| -.1072324 .3103702 -0.35 0.730 -.7155469 .5010821 12 \| -.0684838 .4560902 -0.15 0.881 -.9624041 .8254366 13 \| -.5364663 .3582739 -1.50 0.134 -1.23867 .1657376 14 \| -.4103014 .525207 -0.78 0.435 -1.439688 .6190854 15 \| -.916741 .4016627 -2.28 0.022 -1.703985 -.1294966 16 \| .5137234 .445626 1.15 0.249 -.3596875 1.387134 18 \| -.5921128 .3337154 -1.77 0.076 -1.246183 .0619574 19 \| -.3325689 .4205156 -0.79 0.429 -1.156764 .4916266 20 \| .988769 .4289826 2.30 0.021 .1479785 1.829559 21 \| -.8001148 .549299 -1.46 0.145 -1.876721 .2764915 22 \| -.3410793 .3984938 -0.86 0.392 -1.122113 .4399543 23 \| -.0378115 .337763 -0.11 0.911 -.6998148 .6241918 24 \| -.2184652 .3381983 -0.65 0.518 -.8813217 .4443912 25 \| -.3351321 .3293585 -1.02 0.309 -.980663 .3103987 \| experience~g \| -.02985 .0260438 -1.15 0.252 -.080895 .021195 experience~q \| .0638069 .0716646 0.89 0.373 -.0766531 .204267 share_top_~s \| -.0275563 .178107 -0.15 0.877 -.3766395 .321527 share_top_~d \| -.420389 .1733485 -2.43 0.015 -.7601458 -.0806322 \| ireport \| 3 \| .5736708 .1927511 2.98 0.003 .1958855 .9514561 4 \| 0 (omitted) \| authored_s~o \| .177324 .1657397 1.07 0.285 -.1475199 .5021679 share_fema~s \| .2084027 .1835765 1.14 0.256 -.1514007 .568206 editor_pre~t \| .0338833 .1570289 0.22 0.829 -.2738876 .3416542 _cons \| .0413152 .4068878 0.10 0.919 -.7561702 .8388005 ------------------------------------------------------------------------------ .
▼	143	`eststo : margins, dydx() post` . eststo : margins, dydx() post Average marginal effects Number of obs = 1,363 Model VCE: Robust Expression: Pr(sign_10pct), predict() dy/dx wrt: DID IV RDD 2018.year 2.unique_j 3.unique_j 4.unique_j 5.unique_j 7.unique_j 8.unique_j 9.unique_j 10.unique_j 11.unique_j 12.unique_j 13.unique_j 14.unique_j 15.unique_j 16.unique_j 18.unique_j 19.unique_j 20.unique_j 21.unique_j 22.unique_j 23.unique_j 24.unique_j 25.unique_j experience_avg experience_avg_sq share_top_authors share_top_phd 3.ireport 4.ireport authored_solo share_female_authors editor_present ------------------------------------------------------------------------------ \| Delta-method \| dy/dx std. err. z P>\|z\| [95% conf. interval] -------------+---------------------------------------------------------------- DID \| .088472 .0600876 1.47 0.141 -.0292975 .2062416 IV \| .0204321 .0540049 0.38 0.705 -.0854157 .1262798 RDD \| -.0807374 .0629968 -1.28 0.200 -.2042089 .042734 \| year \| 2018 \| . (not estimable) \| unique_j \| 2 \| . (not estimable) 3 \| . (not estimable) 4 \| . (not estimable) 5 \| . (not estimable) 7 \| . (not estimable) 8 \| . (not estimable) 9 \| . (not estimable) 10 \| . (not estimable) 11 \| . (not estimable) 12 \| . (not estimable) 13 \| . (not estimable) 14 \| . (not estimable) 15 \| . (not estimable) 16 \| . (not estimable) 18 \| . (not estimable) 19 \| . (not estimable) 20 \| . (not estimable) 21 \| . (not estimable) 22 \| . (not estimable) 23 \| . (not estimable) 24 \| . (not estimable) 25 \| . (not estimable) \| experience~g \| -.0107312 .0093345 -1.15 0.250 -.0290266 .0075641 experience~q \| .0229389 .0257002 0.89 0.372 -.0274325 .0733103 share_top_~s \| -.0099066 .0639981 -0.15 0.877 -.1353405 .1155273 share_top_~d \| -.1511319 .0615993 -2.45 0.014 -.2718643 -.0303995 \| ireport \| 3 \| . (not estimable) 4 \| . (not estimable) \| authored_s~o \| .0637489 .0592532 1.08 0.282 -.0523853 .179883 share_fema~s \| .0749218 .0661596 1.13 0.257 -.0547485 .2045921 editor_pre~t \| .0121812 .0564288 0.22 0.829 -.0984173 .1227797 ------------------------------------------------------------------------------ Note: dy/dx for factor levels is the discrete change from the base level. (est6 stored) .
▼	144	estadd local Window "[`threshold'$\pm$0.20]" estadd local Window "[1.65$\pm$0.20]" . estadd local Window "[`threshold'$\pm$0.20]" added macro: e(Window) : "[1.65$\pm$0.20]" .
▼	145	sum `depvar' if t>(`threshold'-0.2) & t<(`threshold'+0.2) & method=="RCT" sum sign_10pct if t>(1.65-0.2) & t<(1.65+0.2) & method=="RCT" . sum `depvar' if t>(`threshold'-0.2) & t<(`threshold'+0.2) > & method=="RCT" Variable \| Obs Mean Std. dev. Min Max -------------+--------------------------------------------------------- sign_10pct \| 484 .5392562 .4989723 0 1 .
▼	146	`estadd local rct_sign = round(r(mean), 0.01)` `. estadd local rct_sign = round(r(mean), 0.01) added macro: e(rct_sign) : ".54" .`
	147
▼	148	`esttab, margin ///` esttab, margin keep(DID IV RDD top5 2018.year experience_avg experience_avg_sq share_top_authors share_top_phd ) label stats(N Window rct_sign, fmt(%9.0fc) labels("Observations" "Window" "RCT sig rate")) . esttab, margin keep(DID IV RDD top5 2018.year experience_a > vg experience_avg_sq share_top_authors share_top_phd ) label stats(N Window r > ct_sign, fmt(%9.0fc) labels("Observations" "Window" "RCT sig rate")) ------------------------------------------------------------------------------- > ------------------------------------- (1) (2) (3) ( > 4) (5) (6) > ------------------------------------------------------------------------------- > ------------------------------------- DID 0.100* 0.113 0.108 0.1 > 11** 0.103* 0.0885 (2.30) (2.82) (2.63) (2.6 > 7) (2.18) (1.47) IV 0.116 0.126* 0.101* 0.1 > 11** 0.0659 0.0204 (3.20) (3.36) (2.51) (2.7 > 4) (1.54) (0.38) RDD 0.0151 0.00861 0.00449 0.005 > 10 -0.0240 -0.0807 (0.35) (0.21) (0.10) (0.1 > 1) (-0.43) (-1.28) Top 5 0.0599 -0.0473 > (1.23) (-0.46) > Year=2018 0.00312 0.0102 0.01 > 97 0.0238 0 (0.09) (0.30) (0.5 > 7) (0.65) (.) Experience -0.00183 -0.00553 -0.006 > 58 -0.0155* -0.0107 (-0.21) (-0.64) (-0.8 > 0) (-1.96) (-1.15) Experience squared -0.00323 0.00786 0.008 > 72 0.0318 0.0229 (-0.12) (0.30) (0.3 > 6) (1.36) (0.89) Top institution -0.0574 -0.0443 -0.03 > 89 -0.00590 -0.00991 (-1.18) (-0.90) (-0.8 > 0) (-0.11) (-0.15) Top PhD institution -0.0162 -0.0324 -0.04 > 46 -0.0595 -0.151* (-0.36) (-0.73) (-1.0 > 3) (-1.21) (-2.45) ------------------------------------------------------------------------------- > ------------------------------------- Observations 3,470 3,470 3,470 3,4 > 69 2,377 1,363 Window [1.65$\pm$0.50] [1.65$\pm$0.50] [1.65$\pm$0.50] [ > 1.65$\pm$0.50] [1.65$\pm$0.35] [1.65$\pm$0.20] RCT sig rate .52 .52 .52 . > 52 .53 .54 ------------------------------------------------------------------------------- > ------------------------------------- Marginal effects; t statistics in parentheses (d) for discrete change of dummy variable from 0 to 1 * p<0.05, p<0.01, * p<0.001 .
	149	`keep(DID IV RDD top5 2018.year experience_avg experience_avg_sq share_top_authors share_top_phd ) label stats(N Window rct_sign, fmt(%9.0fc) labels("Observations" "Window" "RCT sig rate"))`
	150
▼	151	esttab using table_A5_caliper_`depvar'.tex, margin /// esttab using table_A5_caliper_sign_10pct.tex, margin keep(DID IV RDD top5 2018.year experience_avg experience_avg_sq share_top_authors share_top_phd) label stats(N Window rct_sign, fmt(%9.0fc) labels("Observations" "Window" "RCT sig rate")) mtitles() nomtitles nostar compress se(3) b(3) replace nogaps noomitted indicate( "Reporting Method = ireport" "Solo Authored = authored_solo" "Share Female Authors = share_female_authors" "Editor = editor_present" "Field FE = FINANCE" "Journal FE = unique_j" , labels("Y" " ")) nonotes . esttab using "table_A5_caliper_sign_10pct.tex", margin keep(DID IV > RDD top5 2018.year experience_avg experience_avg_sq share_top_authors share_t > op_phd) label stats(N Window rct_sign, fmt(%9.0fc) labels("Observations" "Wi > ndow" "RCT sig rate")) mtitles() nomtitles nostar compress se(3) b(3) replace > nogaps noomitted indicate( "Reporting Method = ireport" "Solo Authored = au > thored_solo" "Share Female Authors = share_female_authors" "Editor = editor_p > resent" "Field FE = FINANCE" "Journal FE = unique_j" , labels("Y" " ")) nono > tes (output written to table_A5_caliper_sign_10pct.tex) .
	152	`keep(DID IV RDD top5 2018.year experience_avg experience_avg_sq share_top_authors share_top_phd) label stats(N Window rct_sign, fmt(%9.0fc) labels("Observations" "Window" "RCT sig rate")) ///`
	153	`mtitles() nomtitles nostar ///`
	154	`compress se(3) b(3) replace nogaps noomitted ///`
	155	`indicate( ///`
	156	`"Reporting Method = *ireport" ///`
	157	`"Solo Authored = authored_solo" ///`
	158	`"Share Female Authors = share_female_authors" ///`
	159	`"Editor = editor_present" ///`
	160	`"Field FE = FINANCE" ///`
	161	`"Journal FE = *unique_j" ///`
	162	`, labels("Y" " ")) ///`
	163	`nonotes`
	164
	165
	166
	167	`** Table A6: 1% significance treshold`
	168
	169	`* read in the data`
▼	170	`cd "$dir_data"` `cd "/home/rstudio/repbox/projects_ejd/aer_112_9_9/mod/Scripts/Data" . cd "${repbox_path}/Data" /home/rstudio/repbox/projects_ejd/aer_112_9_9/mod/Data .`
▼	171	`capture use "MM_new.dta", clear` `. capture use "MM_new.dta", clear .`
	172
	173	`* determine folder to store results`
▼	174	`cd "$dir_results"` `cd "/home/rstudio/repbox/projects_ejd/aer_112_9_9/mod/Scripts/Results" . cd "${repbox_path}/Results" /home/rstudio/repbox/projects_ejd/aer_112_9_9/mod/Results .`
	175
	176
	177	`* drop obs with small significand`
▼	178	`keep if keep_obs==1` `. keep if keep_obs==1 (8,233 observations deleted) .`
	179
	180
▼	181	`local depvar "sign_1pct"` `. local depvar "sign_1pct" .`
▼	182	`local threshold 2.58` `. local threshold 2.58 .`
▼	183	`local weight1 "pw="` `. local weight1 "pw=" .`
▼	184	`local weight2 "aw"` `. local weight2 "aw" .`
	185
	186
▼	187	`eststo clear` `. eststo clear .`
	188
▼	189	probit `depvar' DID IV RDD if t>(`threshold'-0.5) & t<(`threshold'+0.5) [`weight1'`weight2'], cluster(journal_article_cluster) probit sign_1pct DID IV RDD if t>(2.58-0.5) & t<(2.58+0.5) [pw=aw], cluster(journal_article_cluster) . probit `depvar' DID IV RDD if t>(`threshold'-0.5) & t<(`th > reshold'+0.5) [`weight1'`weight2'], cluster(journal_article_cluster) Iteration 0: log pseudolikelihood = -669750.1 Iteration 1: log pseudolikelihood = -667247.48 Iteration 2: log pseudolikelihood = -667246.54 Iteration 3: log pseudolikelihood = -667246.54 Probit regression Number of obs = 2,689 Wald chi2(3) = 3.44 Prob > chi2 = 0.3286 Log pseudolikelihood = -667246.54 Pseudo R2 = 0.0037 (Std. err. adjusted for 461 clusters in journal_article_cluster) ------------------------------------------------------------------------------ \| Robust sign_1pct \| Coefficient std. err. z P>\|z\| [95% conf. interval] -------------+---------------------------------------------------------------- DID \| .1289408 .1248527 1.03 0.302 -.115766 .3736476 IV \| .0500791 .1090326 0.46 0.646 -.1636209 .263779 RDD \| -.2116945 .1757407 -1.20 0.228 -.55614 .1327509 _cons \| -.2623067 .0748966 -3.50 0.000 -.4091014 -.1155121 ------------------------------------------------------------------------------ .
▼	190	`eststo : margins, dydx() post` . eststo : margins, dydx() post Average marginal effects Number of obs = 2,689 Model VCE: Robust Expression: Pr(sign_1pct), predict() dy/dx wrt: DID IV RDD ------------------------------------------------------------------------------ \| Delta-method \| dy/dx std. err. z P>\|z\| [95% conf. interval] -------------+---------------------------------------------------------------- DID \| .0500332 .0485232 1.03 0.302 -.0450705 .1451368 IV \| .0194323 .0423733 0.46 0.647 -.0636178 .1024824 RDD \| -.0821443 .0678584 -1.21 0.226 -.2151443 .0508557 ------------------------------------------------------------------------------ (est1 stored) .
▼	191	estadd local Window "[`threshold'$\pm$0.50]" estadd local Window "[2.58$\pm$0.50]" . estadd local Window "[`threshold'$\pm$0.50]" added macro: e(Window) : "[2.58$\pm$0.50]" .
▼	192	sum `depvar' if t>(`threshold'-0.5) & t<(`threshold'+0.5) & method=="RCT" sum sign_1pct if t>(2.58-0.5) & t<(2.58+0.5) & method=="RCT" . sum `depvar' if t>(`threshold'-0.5) & t<(`threshold'+0.5) > & method=="RCT" Variable \| Obs Mean Std. dev. Min Max -------------+--------------------------------------------------------- sign_1pct \| 741 .3711201 .4834308 0 1 .
▼	193	`estadd local rct_sign = round(r(mean), 0.01)` `. estadd local rct_sign = round(r(mean), 0.01) added macro: e(rct_sign) : ".37" .`
	194
▼	195	probit `depvar' DID IV RDD top5 i.year experience_avg experience_avg_sq share_top_authors share_top_phd i.ireport authored_solo share_female_authors editor_present if t>(`threshold'-0.5) & t<(`threshold'+0.5) [`weight1'`weight2'], cluster(journal_article_cluster) probit sign_1pct DID IV RDD top5 i.year experience_avg experience_avg_sq share_top_authors share_top_phd i.ireport authored_solo share_female_authors editor_present if t>(2.58-0.5) & t<(2.58+0.5) [pw=aw], cluster(journal_article_cluster) . probit `depvar' DID IV RDD top5 i.year experience_avg expe > rience_avg_sq share_top_authors share_top_phd i.ireport authored_solo share_f > emale_authors editor_present if t>(`threshold'-0.5) & t<(`threshold'+0.5) [`w > eight1'`weight2'], cluster(journal_article_cluster) Iteration 0: log pseudolikelihood = -669750.1 Iteration 1: log pseudolikelihood = -659017.59 Iteration 2: log pseudolikelihood = -659006.41 Iteration 3: log pseudolikelihood = -659006.41 Probit regression Number of obs = 2,689 Wald chi2(15) = 19.56 Prob > chi2 = 0.1894 Log pseudolikelihood = -659006.41 Pseudo R2 = 0.0160 (Std. err. adjusted for 461 clusters in journal_article_cluster) ------------------------------------------------------------------------------ \| Robust sign_1pct \| Coefficient std. err. z P>\|z\| [95% conf. interval] -------------+---------------------------------------------------------------- DID \| .1049754 .1180157 0.89 0.374 -.1263311 .3362819 IV \| .0227496 .1027472 0.22 0.825 -.1786313 .2241305 RDD \| -.215545 .1626261 -1.33 0.185 -.5342862 .1031962 top5 \| .0749811 .1456956 0.51 0.607 -.210577 .3605392 \| year \| 2018 \| .0267661 .1063027 0.25 0.801 -.1815833 .2351156 \| experience~g \| .0469408 .0246645 1.90 0.057 -.0014006 .0952823 experience~q \| -.1289768 .0790245 -1.63 0.103 -.283862 .0259084 share_top_~s \| .0083037 .1623162 0.05 0.959 -.3098302 .3264376 share_top_~d \| -.1335537 .1391907 -0.96 0.337 -.4063625 .1392551 \| ireport \| 2 \| .118627 .768349 0.15 0.877 -1.387309 1.624563 3 \| .2407662 .7534585 0.32 0.749 -1.235985 1.717518 4 \| .0756213 .7685389 0.10 0.922 -1.430687 1.58193 \| authored_s~o \| .1635069 .1340453 1.22 0.223 -.0992172 .4262309 share_fema~s \| -.3373093 .1435892 -2.35 0.019 -.618739 -.0558796 editor_pre~t \| -.0011926 .1313088 -0.01 0.993 -.2585531 .256168 _cons \| -.7068931 .7791257 -0.91 0.364 -2.233951 .8201652 ------------------------------------------------------------------------------ .
▼	196	`eststo : margins, dydx() post` . eststo : margins, dydx() post Average marginal effects Number of obs = 2,689 Model VCE: Robust Expression: Pr(sign_1pct), predict() dy/dx wrt: DID IV RDD top5 2018.year experience_avg experience_avg_sq share_top_authors share_top_phd 2.ireport 3.ireport 4.ireport authored_solo share_female_authors editor_present ------------------------------------------------------------------------------ \| Delta-method \| dy/dx std. err. z P>\|z\| [95% conf. interval] -------------+---------------------------------------------------------------- DID \| .0401893 .0453022 0.89 0.375 -.0486014 .12898 IV \| .0087096 .0393635 0.22 0.825 -.0684414 .0858606 RDD \| -.0825202 .0618957 -1.33 0.182 -.2038335 .038793 top5 \| .0287061 .0557322 0.52 0.607 -.0805269 .1379392 \| year \| 2018 \| .0102445 .040671 0.25 0.801 -.0694692 .0899583 \| experience~g \| .017971 .0093974 1.91 0.056 -.0004476 .0363897 experience~q \| -.0493781 .0301451 -1.64 0.101 -.1084614 .0097053 share_top_~s \| .003179 .0621443 0.05 0.959 -.1186215 .1249796 share_top_~d \| -.0511303 .0532617 -0.96 0.337 -.1555213 .0532606 \| ireport \| 2 \| .043468 .275852 0.16 0.875 -.497192 .5841281 3 \| .0898759 .2700094 0.33 0.739 -.4393328 .6190846 4 \| .0274979 .2757206 0.10 0.921 -.5129046 .5679003 \| authored_s~o \| .0625977 .0511927 1.22 0.221 -.0377381 .1629336 share_fema~s \| -.129137 .0543453 -2.38 0.017 -.2356519 -.0226222 editor_pre~t \| -.0004566 .0502704 -0.01 0.993 -.0989847 .0980716 ------------------------------------------------------------------------------ Note: dy/dx for factor levels is the discrete change from the base level. (est2 stored) .
▼	197	estadd local Window "[`threshold'$\pm$0.50]" estadd local Window "[2.58$\pm$0.50]" . estadd local Window "[`threshold'$\pm$0.50]" added macro: e(Window) : "[2.58$\pm$0.50]" .
▼	198	sum `depvar' if t>(`threshold'-0.5) & t<(`threshold'+0.5) & method=="RCT" sum sign_1pct if t>(2.58-0.5) & t<(2.58+0.5) & method=="RCT" . sum `depvar' if t>(`threshold'-0.5) & t<(`threshold'+0.5) > & method=="RCT" Variable \| Obs Mean Std. dev. Min Max -------------+--------------------------------------------------------- sign_1pct \| 741 .3711201 .4834308 0 1 .
▼	199	`estadd local rct_sign = round(r(mean), 0.01)` `. estadd local rct_sign = round(r(mean), 0.01) added macro: e(rct_sign) : ".37" .`
	200
▼	201	probit `depvar' DID IV RDD top5 i.year FINANCE MACRO_GROWTH GEN_INT EXP DEV LABOR PUB URB experience_avg experience_avg_sq share_top_authors share_top_phd i.ireport authored_solo share_female_authors editor_present if t>(`threshold'-0.5) & t<(`threshold'+0.5) [`weight1'`weight2'], cluster(journal_article_cluster) probit sign_1pct DID IV RDD top5 i.year FINANCE MACRO_GROWTH GEN_INT EXP DEV LABOR PUB URB experience_avg experience_avg_sq share_top_authors share_top_phd i.ireport authored_solo share_female_authors editor_present if t>(2.58-0.5) & t<(2.58+0.5) [pw=aw], cluster(journal_article_cluster) . probit `depvar' DID IV RDD top5 i.year FINANCE MACRO_GROWT > H GEN_INT EXP DEV LABOR PUB URB experience_avg experience_avg_sq share_top_au > thors share_top_phd i.ireport authored_solo share_female_authors editor_prese > nt if t>(`threshold'-0.5) & t<(`threshold'+0.5) [`weight1'`weight2'], cluster > (journal_article_cluster) Iteration 0: log pseudolikelihood = -669750.1 Iteration 1: log pseudolikelihood = -656965.52 Iteration 2: log pseudolikelihood = -656953.8 Iteration 3: log pseudolikelihood = -656953.8 Probit regression Number of obs = 2,689 Wald chi2(23) = 26.71 Prob > chi2 = 0.2687 Log pseudolikelihood = -656953.8 Pseudo R2 = 0.0191 (Std. err. adjusted for 461 clusters in journal_article_cluster) ------------------------------------------------------------------------------ \| Robust sign_1pct \| Coefficient std. err. z P>\|z\| [95% conf. interval] -------------+---------------------------------------------------------------- DID \| .0561092 .1253168 0.45 0.654 -.1895072 .3017255 IV \| -.0455817 .1054459 -0.43 0.666 -.2522519 .1610885 RDD \| -.2450737 .1638788 -1.50 0.135 -.5662703 .0761229 top5 \| -.2633865 .2643093 -1.00 0.319 -.7814233 .2546502 \| year \| 2018 \| .0221047 .1080531 0.20 0.838 -.1896755 .2338848 \| FINANCE \| -.2517506 .2609974 -0.96 0.335 -.7632962 .2597949 MACRO_GROWTH \| -.1471067 .4009632 -0.37 0.714 -.9329802 .6387667 GEN_INT \| -.3894207 .2388287 -1.63 0.103 -.8575165 .078675 EXP \| -.2147162 .2502937 -0.86 0.391 -.7052828 .2758504 DEV \| -.4519424 .2827011 -1.60 0.110 -1.006026 .1021416 LABOR \| -.4441472 .2614634 -1.70 0.089 -.9566061 .0683117 PUB \| -.4125309 .2626777 -1.57 0.116 -.9273697 .1023079 URB \| -.2745804 .3170516 -0.87 0.386 -.8959902 .3468294 experience~g \| .0421548 .0238079 1.77 0.077 -.0045079 .0888174 experience~q \| -.1146504 .0760567 -1.51 0.132 -.2637189 .0344181 share_top_~s \| .0168047 .1645871 0.10 0.919 -.30578 .3393894 share_top_~d \| -.1379511 .1406996 -0.98 0.327 -.4137172 .1378151 \| ireport \| 2 \| .0414204 .7575666 0.05 0.956 -1.443383 1.526224 3 \| .1976292 .7418961 0.27 0.790 -1.25646 1.651719 4 \| -.0405008 .7634453 -0.05 0.958 -1.536826 1.455825 \| authored_s~o \| .139048 .1340644 1.04 0.300 -.1237134 .4018094 share_fema~s \| -.3471497 .1417911 -2.45 0.014 -.6250551 -.0692442 editor_pre~t \| -.032286 .1341003 -0.24 0.810 -.2951178 .2305457 _cons \| -.212291 .8107186 -0.26 0.793 -1.80127 1.376688 ------------------------------------------------------------------------------ .
▼	202	`eststo : margins, dydx() post` . eststo : margins, dydx() post Average marginal effects Number of obs = 2,689 Model VCE: Robust Expression: Pr(sign_1pct), predict() dy/dx wrt: DID IV RDD top5 2018.year FINANCE MACRO_GROWTH GEN_INT EXP DEV LABOR PUB URB experience_avg experience_avg_sq share_top_authors share_top_phd 2.ireport 3.ireport 4.ireport authored_solo share_female_authors editor_present ------------------------------------------------------------------------------ \| Delta-method \| dy/dx std. err. z P>\|z\| [95% conf. interval] -------------+---------------------------------------------------------------- DID \| .0214101 .0478951 0.45 0.655 -.0724626 .1152828 IV \| -.0173931 .0401725 -0.43 0.665 -.0961298 .0613437 RDD \| -.0935152 .0620886 -1.51 0.132 -.2152066 .0281763 top5 \| -.100503 .1006628 -1.00 0.318 -.2977985 .0967925 \| year \| 2018 \| .008433 .0412074 0.20 0.838 -.0723321 .0891981 \| FINANCE \| -.096063 .0993545 -0.97 0.334 -.2907943 .0986684 MACRO_GROWTH \| -.056133 .1529368 -0.37 0.714 -.3558836 .2436177 GEN_INT \| -.1485951 .0907006 -1.64 0.101 -.326365 .0291749 EXP \| -.0819314 .0954957 -0.86 0.391 -.2690994 .1052367 DEV \| -.1724521 .107272 -1.61 0.108 -.3827012 .0377971 LABOR \| -.1694776 .0994083 -1.70 0.088 -.3643143 .0253591 PUB \| -.1574135 .099665 -1.58 0.114 -.3527533 .0379264 URB \| -.1047743 .1207954 -0.87 0.386 -.341529 .1319804 experience~g \| .0160854 .0090547 1.78 0.076 -.0016615 .0338323 experience~q \| -.0437483 .0289627 -1.51 0.131 -.1005141 .0130175 share_top_~s \| .0064123 .062806 0.10 0.919 -.1166851 .1295097 share_top_~d \| -.0526393 .0536604 -0.98 0.327 -.1578118 .0525331 \| ireport \| 2 \| .0152065 .27631 0.06 0.956 -.5263512 .5567641 3 \| .0742071 .2704563 0.27 0.784 -.4558775 .6042917 4 \| -.0146494 .2779867 -0.05 0.958 -.5594934 .5301946 \| authored_s~o \| .0530579 .0510538 1.04 0.299 -.0470057 .1531215 share_fema~s \| -.1324653 .0533958 -2.48 0.013 -.2371192 -.0278114 editor_pre~t \| -.0123197 .051149 -0.24 0.810 -.1125699 .0879305 ------------------------------------------------------------------------------ Note: dy/dx for factor levels is the discrete change from the base level. (est3 stored) .
▼	203	estadd local Window "[`threshold'$\pm$0.50]" estadd local Window "[2.58$\pm$0.50]" . estadd local Window "[`threshold'$\pm$0.50]" added macro: e(Window) : "[2.58$\pm$0.50]" .
▼	204	sum `depvar' if t>(`threshold'-0.5) & t<(`threshold'+0.5) & method=="RCT" sum sign_1pct if t>(2.58-0.5) & t<(2.58+0.5) & method=="RCT" . sum `depvar' if t>(`threshold'-0.5) & t<(`threshold'+0.5) > & method=="RCT" Variable \| Obs Mean Std. dev. Min Max -------------+--------------------------------------------------------- sign_1pct \| 741 .3711201 .4834308 0 1 .
▼	205	`estadd local rct_sign = round(r(mean), 0.01)` `. estadd local rct_sign = round(r(mean), 0.01) added macro: e(rct_sign) : ".37" .`
	206
▼	207	probit `depvar' DID IV RDD i.year i.unique_j experience_avg experience_avg_sq share_top_authors share_top_phd i.ireport authored_solo share_female_authors editor_present if t>(`threshold'-0.5) & t<(`threshold'+0.5) [`weight1'`weight2'], cluster(journal_article_cluster) probit sign_1pct DID IV RDD i.year i.unique_j experience_avg experience_avg_sq share_top_authors share_top_phd i.ireport authored_solo share_female_authors editor_present if t>(2.58-0.5) & t<(2.58+0.5) [pw=aw], cluster(journal_article_cluster) . probit `depvar' DID IV RDD i.year i.unique_j experience_av > g experience_avg_sq share_top_authors share_top_phd i.ireport authored_solo s > hare_female_authors editor_present if t>(`threshold'-0.5) & t<(`threshold'+0. > 5) [`weight1'`weight2'], cluster(journal_article_cluster) Iteration 0: log pseudolikelihood = -669750.1 Iteration 1: log pseudolikelihood = -641856.54 Iteration 2: log pseudolikelihood = -641691.24 Iteration 3: log pseudolikelihood = -641690.99 Iteration 4: log pseudolikelihood = -641690.99 Probit regression Number of obs = 2,689 Wald chi2(38) = 54.12 Prob > chi2 = 0.0434 Log pseudolikelihood = -641690.99 Pseudo R2 = 0.0419 (Std. err. adjusted for 461 clusters in journal_article_cluster) ------------------------------------------------------------------------------ \| Robust sign_1pct \| Coefficient std. err. z P>\|z\| [95% conf. interval] -------------+---------------------------------------------------------------- DID \| .0257111 .1301481 0.20 0.843 -.2293744 .2807967 IV \| -.1059543 .112491 -0.94 0.346 -.3264326 .114524 RDD \| -.2465012 .1743136 -1.41 0.157 -.5881497 .0951472 \| year \| 2018 \| .0589941 .1116136 0.53 0.597 -.1597646 .2777528 \| unique_j \| 2 \| .2956642 .4679035 0.63 0.527 -.6214099 1.212738 3 \| .5506824 .3473928 1.59 0.113 -.130195 1.23156 4 \| .026867 .253102 0.11 0.915 -.4692039 .5229379 5 \| .2489778 .3416742 0.73 0.466 -.4206913 .9186469 6 \| -.4094304 .5102086 -0.80 0.422 -1.409421 .59056 7 \| .5991428 .4718049 1.27 0.204 -.3255779 1.523863 8 \| .1029652 .2790941 0.37 0.712 -.4440491 .6499795 9 \| .1646734 .2721574 0.61 0.545 -.3687453 .6980922 10 \| .1995355 .2126906 0.94 0.348 -.2173305 .6164014 11 \| .1079337 .2305514 0.47 0.640 -.3439387 .5598062 12 \| -.2598078 .274835 -0.95 0.344 -.7984745 .2788589 13 \| -.0620644 .2642471 -0.23 0.814 -.5799792 .4558503 14 \| .4792887 .2840772 1.69 0.092 -.0774924 1.03607 15 \| .1370836 .261072 0.53 0.600 -.3746082 .6487753 16 \| .2360148 .2591621 0.91 0.362 -.2719336 .7439633 17 \| .2279155 .2247168 1.01 0.310 -.2125213 .6683524 18 \| -.0419797 .2487263 -0.17 0.866 -.5294743 .4455149 19 \| .0138106 .238701 0.06 0.954 -.4540347 .4816559 20 \| 1.273893 .4055921 3.14 0.002 .478947 2.068839 21 \| -1.526916 .8057508 -1.90 0.058 -3.106158 .0523268 22 \| .0904133 .2350773 0.38 0.701 -.3703297 .5511564 23 \| -.102508 .306142 -0.33 0.738 -.7025354 .4975193 24 \| .1905859 .2934376 0.65 0.516 -.3845413 .765713 25 \| .0710025 .2508327 0.28 0.777 -.4206205 .5626254 \| experience~g \| .0352558 .0239867 1.47 0.142 -.0117572 .0822688 experience~q \| -.1005329 .0758881 -1.32 0.185 -.2492709 .0482051 share_top_~s \| .0167082 .1652389 0.10 0.919 -.3071541 .3405705 share_top_~d \| -.1018654 .1500139 -0.68 0.497 -.3958872 .1921565 \| ireport \| 2 \| -.7766744 .5102179 -1.52 0.128 -1.776683 .2233343 3 \| -.5604131 .4816508 -1.16 0.245 -1.504431 .3836052 4 \| -.7461254 .5136793 -1.45 0.146 -1.752918 .2606676 \| authored_s~o \| .1368841 .1411598 0.97 0.332 -.1397841 .4135523 share_fema~s \| -.3152116 .131669 -2.39 0.017 -.573278 -.0571451 editor_pre~t \| -.0606189 .1388297 -0.44 0.662 -.3327202 .2114824 _cons \| .1723919 .5047188 0.34 0.733 -.8168388 1.161622 ------------------------------------------------------------------------------ .
▼	208	`eststo : margins, dydx() post` . eststo : margins, dydx() post Average marginal effects Number of obs = 2,689 Model VCE: Robust Expression: Pr(sign_1pct), predict() dy/dx wrt: DID IV RDD 2018.year 2.unique_j 3.unique_j 4.unique_j 5.unique_j 6.unique_j 7.unique_j 8.unique_j 9.unique_j 10.unique_j 11.unique_j 12.unique_j 13.unique_j 14.unique_j 15.unique_j 16.unique_j 17.unique_j 18.unique_j 19.unique_j 20.unique_j 21.unique_j 22.unique_j 23.unique_j 24.unique_j 25.unique_j experience_avg experience_avg_sq share_top_authors share_top_phd 2.ireport 3.ireport 4.ireport authored_solo share_female_authors editor_present ------------------------------------------------------------------------------ \| Delta-method \| dy/dx std. err. z P>\|z\| [95% conf. interval] -------------+---------------------------------------------------------------- DID \| .0095712 .0484743 0.20 0.843 -.0854368 .1045791 IV \| -.0394422 .0417182 -0.95 0.344 -.1212083 .0423239 RDD \| -.0917618 .0645585 -1.42 0.155 -.2182941 .0347705 \| year \| 2018 \| .0219448 .0414626 0.53 0.597 -.0593204 .1032099 \| unique_j \| 2 \| .1137101 .1822399 0.62 0.533 -.2434735 .4708937 3 \| .2132205 .1323746 1.61 0.107 -.046229 .4726699 4 \| .0100275 .0944197 0.11 0.915 -.1750317 .1950867 5 \| .0954176 .1318662 0.72 0.469 -.1630355 .3538707 6 \| -.1387854 .1581679 -0.88 0.380 -.4487887 .1712179 7 \| .231731 .1786678 1.30 0.195 -.1184514 .5819134 8 \| .0388489 .1054654 0.37 0.713 -.1678595 .2455573 9 \| .0625955 .1036011 0.60 0.546 -.140459 .26565 10 \| .0761252 .0801135 0.95 0.342 -.0808943 .2331448 11 \| .0407498 .0866792 0.47 0.638 -.1291382 .2106378 12 \| -.0915933 .0959825 -0.95 0.340 -.2797154 .0965289 13 \| -.0228191 .0971173 -0.23 0.814 -.2131655 .1675273 14 \| .1856215 .1084807 1.71 0.087 -.0269968 .3982399 15 \| .0519429 .0988254 0.53 0.599 -.1417514 .2456372 16 \| .0903498 .0988365 0.91 0.361 -.1033663 .2840658 17 \| .0871866 .0850802 1.02 0.305 -.0795676 .2539407 18 \| -.0154903 .0918156 -0.17 0.866 -.1954456 .1644649 19 \| .0051439 .0888756 0.06 0.954 -.169049 .1793369 20 \| .4516789 .1150449 3.93 0.000 .226195 .6771628 21 \| -.3366742 .0843757 -3.99 0.000 -.5020475 -.1713008 22 \| .0340564 .088233 0.39 0.700 -.138877 .2069898 23 \| -.0374022 .110967 -0.34 0.736 -.2548935 .1800891 24 \| .0726453 .1122336 0.65 0.517 -.1473284 .2926191 25 \| .0266734 .0941321 0.28 0.777 -.1578221 .2111689 \| experience~g \| .0131242 .0089164 1.47 0.141 -.0043516 .0306 experience~q \| -.0374241 .028219 -1.33 0.185 -.0927323 .0178842 share_top_~s \| .0062197 .0615088 0.10 0.919 -.1143353 .1267748 share_top_~d \| -.0379201 .0557846 -0.68 0.497 -.1472558 .0714157 \| ireport \| 2 \| -.2896501 .1825896 -1.59 0.113 -.6475192 .0682189 3 \| -.2107436 .1729875 -1.22 0.223 -.5497929 .1283056 4 \| -.2788188 .1841608 -1.51 0.130 -.6397672 .0821297 \| authored_s~o \| .0509561 .0524771 0.97 0.332 -.0518972 .1538093 share_fema~s \| -.1173397 .0485035 -2.42 0.016 -.2124047 -.0222747 editor_pre~t \| -.0225658 .0516462 -0.44 0.662 -.1237904 .0786588 ------------------------------------------------------------------------------ Note: dy/dx for factor levels is the discrete change from the base level. (est4 stored) .
▼	209	estadd local Window "[`threshold'$\pm$0.50]" estadd local Window "[2.58$\pm$0.50]" . estadd local Window "[`threshold'$\pm$0.50]" added macro: e(Window) : "[2.58$\pm$0.50]" .
▼	210	sum `depvar' if t>(`threshold'-0.5) & t<(`threshold'+0.5) & method=="RCT" sum sign_1pct if t>(2.58-0.5) & t<(2.58+0.5) & method=="RCT" . sum `depvar' if t>(`threshold'-0.5) & t<(`threshold'+0.5) > & method=="RCT" Variable \| Obs Mean Std. dev. Min Max -------------+--------------------------------------------------------- sign_1pct \| 741 .3711201 .4834308 0 1 .
▼	211	`estadd local rct_sign = round(r(mean), 0.01)` `. estadd local rct_sign = round(r(mean), 0.01) added macro: e(rct_sign) : ".37" .`
	212
▼	213	probit `depvar' DID IV RDD i.year i.unique_j experience_avg experience_avg_sq share_top_authors share_top_phd i.ireport authored_solo share_female_authors editor_present if t>(`threshold'-0.35) & t<(`threshold'+0.35) [`weight1'`weight2'], cluster(journal_article_cluster) probit sign_1pct DID IV RDD i.year i.unique_j experience_avg experience_avg_sq share_top_authors share_top_phd i.ireport authored_solo share_female_authors editor_present if t>(2.58-0.35) & t<(2.58+0.35) [pw=aw], cluster(journal_article_cluster) . probit `depvar' DID IV RDD i.year i.unique_j experience_av > g experience_avg_sq share_top_authors share_top_phd i.ireport authored_solo s > hare_female_authors editor_present if t>(`threshold'-0.35) & t<(`threshold'+0 > .35) [`weight1'`weight2'], cluster(journal_article_cluster) note: 1.ireport != 0 predicts failure perfectly; 1.ireport omitted and 1 obs not used. note: 4.ireport omitted because of collinearity. Iteration 0: log pseudolikelihood = -447631.12 Iteration 1: log pseudolikelihood = -430154.08 Iteration 2: log pseudolikelihood = -430104.52 Iteration 3: log pseudolikelihood = -430104.51 Probit regression Number of obs = 1,850 Wald chi2(36) = 64.68 Prob > chi2 = 0.0023 Log pseudolikelihood = -430104.51 Pseudo R2 = 0.0392 (Std. err. adjusted for 411 clusters in journal_article_cluster) ------------------------------------------------------------------------------ \| Robust sign_1pct \| Coefficient std. err. z P>\|z\| [95% conf. interval] -------------+---------------------------------------------------------------- DID \| .0694135 .1441847 0.48 0.630 -.2131833 .3520104 IV \| -.0486364 .1217521 -0.40 0.690 -.2872661 .1899933 RDD \| -.2004576 .1899846 -1.06 0.291 -.5728206 .1719054 \| year \| 2018 \| .0373967 .1137537 0.33 0.742 -.1855564 .2603498 \| unique_j \| 2 \| .3211505 .6069604 0.53 0.597 -.8684701 1.510771 3 \| .9409668 .2810071 3.35 0.001 .3902029 1.491731 4 \| .001558 .271082 0.01 0.995 -.5297529 .532869 5 \| .9615514 .6286406 1.53 0.126 -.2705615 2.193664 6 \| -.5400524 .7262664 -0.74 0.457 -1.963508 .8834035 7 \| .0320907 .2486539 0.13 0.897 -.4552621 .5194434 8 \| .1020781 .2800466 0.36 0.715 -.4468031 .6509594 9 \| .4289812 .2343286 1.83 0.067 -.0302945 .8882568 10 \| .2512324 .2017984 1.24 0.213 -.1442851 .64675 11 \| .2129032 .2487633 0.86 0.392 -.2746639 .7004702 12 \| .0279251 .3249122 0.09 0.932 -.6088911 .6647413 13 \| .0192811 .2711351 0.07 0.943 -.5121339 .5506961 14 \| .5804223 .2902839 2.00 0.046 .0114764 1.149368 15 \| .0268399 .2832367 0.09 0.925 -.5282938 .5819736 16 \| .345085 .2720131 1.27 0.205 -.1880509 .878221 17 \| -.1002304 .5408 -0.19 0.853 -1.160179 .959718 18 \| .243329 .2607562 0.93 0.351 -.2677438 .7544019 19 \| -.0282034 .2315294 -0.12 0.903 -.4819926 .4255858 20 \| .9469508 .4077359 2.32 0.020 .1478031 1.746099 21 \| -.3966219 .6417485 -0.62 0.537 -1.654426 .8611821 22 \| .2167314 .2335249 0.93 0.353 -.240969 .6744318 23 \| -.1683029 .2905126 -0.58 0.562 -.7376971 .4010914 24 \| .534512 .2960957 1.81 0.071 -.0458249 1.114849 25 \| .2822675 .2642241 1.07 0.285 -.2356022 .8001373 \| experience~g \| .0368621 .0278063 1.33 0.185 -.0176373 .0913616 experience~q \| -.1124292 .1037008 -1.08 0.278 -.315679 .0908207 share_top_~s \| .0015571 .1809837 0.01 0.993 -.3531645 .3562787 share_top_~d \| .0675872 .1692833 0.40 0.690 -.264202 .3993764 \| ireport \| 3 \| .1120985 .1484976 0.75 0.450 -.1789515 .4031485 4 \| 0 (omitted) \| authored_s~o \| .1781958 .1495602 1.19 0.233 -.1149369 .4713284 share_fema~s \| -.2586775 .142706 -1.81 0.070 -.5383761 .0210212 editor_pre~t \| -.0302245 .1400717 -0.22 0.829 -.3047601 .244311 _cons \| -.6583336 .3390612 -1.94 0.052 -1.322881 .0062141 ------------------------------------------------------------------------------ .
▼	214	`eststo : margins, dydx() post` . eststo : margins, dydx() post Average marginal effects Number of obs = 1,850 Model VCE: Robust Expression: Pr(sign_1pct), predict() dy/dx wrt: DID IV RDD 2018.year 2.unique_j 3.unique_j 4.unique_j 5.unique_j 6.unique_j 7.unique_j 8.unique_j 9.unique_j 10.unique_j 11.unique_j 12.unique_j 13.unique_j 14.unique_j 15.unique_j 16.unique_j 17.unique_j 18.unique_j 19.unique_j 20.unique_j 21.unique_j 22.unique_j 23.unique_j 24.unique_j 25.unique_j experience_avg experience_avg_sq share_top_authors share_top_phd 3.ireport 4.ireport authored_solo share_female_authors editor_present ------------------------------------------------------------------------------ \| Delta-method \| dy/dx std. err. z P>\|z\| [95% conf. interval] -------------+---------------------------------------------------------------- DID \| .0263101 .0546511 0.48 0.630 -.0808041 .1334244 IV \| -.0184349 .0461199 -0.40 0.689 -.1088283 .0719585 RDD \| -.0759804 .0717566 -1.06 0.290 -.2166207 .0646599 \| year \| 2018 \| . (not estimable) \| unique_j \| 2 \| . (not estimable) 3 \| . (not estimable) 4 \| . (not estimable) 5 \| . (not estimable) 6 \| . (not estimable) 7 \| . (not estimable) 8 \| . (not estimable) 9 \| . (not estimable) 10 \| . (not estimable) 11 \| . (not estimable) 12 \| . (not estimable) 13 \| . (not estimable) 14 \| . (not estimable) 15 \| . (not estimable) 16 \| . (not estimable) 17 \| . (not estimable) 18 \| . (not estimable) 19 \| . (not estimable) 20 \| . (not estimable) 21 \| . (not estimable) 22 \| . (not estimable) 23 \| . (not estimable) 24 \| . (not estimable) 25 \| . (not estimable) \| experience~g \| .013972 .0105024 1.33 0.183 -.0066124 .0345564 experience~q \| -.0426146 .0392336 -1.09 0.277 -.119511 .0342818 share_top_~s \| .0005902 .0686002 0.01 0.993 -.1338636 .1350441 share_top_~d \| .0256179 .0641246 0.40 0.690 -.1000639 .1512998 \| ireport \| 3 \| . (not estimable) 4 \| . (not estimable) \| authored_s~o \| .0675424 .056457 1.20 0.232 -.0431114 .1781962 share_fema~s \| -.0980478 .0536235 -1.83 0.067 -.2031478 .0070523 editor_pre~t \| -.0114561 .0530783 -0.22 0.829 -.1154878 .0925755 ------------------------------------------------------------------------------ Note: dy/dx for factor levels is the discrete change from the base level. (est5 stored) .
▼	215	estadd local Window "[`threshold'$\pm$0.35]" estadd local Window "[2.58$\pm$0.35]" . estadd local Window "[`threshold'$\pm$0.35]" added macro: e(Window) : "[2.58$\pm$0.35]" .
▼	216	sum `depvar' if t>(`threshold'-0.35) & t<(`threshold'+0.35) & method=="RCT" sum sign_1pct if t>(2.58-0.35) & t<(2.58+0.35) & method=="RCT" . sum `depvar' if t>(`threshold'-0.35) & t<(`threshold'+0.35 > ) & method=="RCT" Variable \| Obs Mean Std. dev. Min Max -------------+--------------------------------------------------------- sign_1pct \| 520 .4153846 .4932627 0 1 .
▼	217	`estadd local rct_sign = round(r(mean), 0.01)` `. estadd local rct_sign = round(r(mean), 0.01) added macro: e(rct_sign) : ".42" .`
	218
▼	219	probit `depvar' DID IV RDD i.year i.unique_j experience_avg experience_avg_sq share_top_authors share_top_phd i.ireport authored_solo share_female_authors editor_present if t>(`threshold'-0.2) & t<(`threshold'+0.2) [`weight1'`weight2'], cluster(journal_article_cluster) probit sign_1pct DID IV RDD i.year i.unique_j experience_avg experience_avg_sq share_top_authors share_top_phd i.ireport authored_solo share_female_authors editor_present if t>(2.58-0.2) & t<(2.58+0.2) [pw=aw], cluster(journal_article_cluster) . probit `depvar' DID IV RDD i.year i.unique_j experience_av > g experience_avg_sq share_top_authors share_top_phd i.ireport authored_solo s > hare_female_authors editor_present if t>(`threshold'-0.2) & t<(`threshold'+0. > 2) [`weight1'`weight2'], cluster(journal_article_cluster) note: 21.unique_j != 0 predicts failure perfectly; 21.unique_j omitted and 1 obs not used. note: 1.ireport != 0 predicts failure perfectly; 1.ireport omitted and 1 obs not used. note: 4.ireport omitted because of collinearity. Iteration 0: log pseudolikelihood = -256050.16 Iteration 1: log pseudolikelihood = -240145.8 Iteration 2: log pseudolikelihood = -240053.29 Iteration 3: log pseudolikelihood = -240053.25 Iteration 4: log pseudolikelihood = -240053.25 Probit regression Number of obs = 1,079 Wald chi2(34) = . Prob > chi2 = . Log pseudolikelihood = -240053.25 Pseudo R2 = 0.0625 (Std. err. adjusted for 344 clusters in journal_article_cluster) ------------------------------------------------------------------------------ \| Robust sign_1pct \| Coefficient std. err. z P>\|z\| [95% conf. interval] -------------+---------------------------------------------------------------- DID \| -.1706136 .1700649 -1.00 0.316 -.5039347 .1627075 IV \| -.0328247 .1618584 -0.20 0.839 -.3500613 .2844118 RDD \| -.3499436 .2648305 -1.32 0.186 -.869002 .1691147 \| year \| 2018 \| .0213381 .126176 0.17 0.866 -.2259623 .2686384 \| unique_j \| 2 \| .0173573 .6029519 0.03 0.977 -1.164407 1.199121 3 \| 1.251681 .7346801 1.70 0.088 -.1882652 2.691628 4 \| .0527726 .3628033 0.15 0.884 -.6583088 .7638539 5 \| 1.740364 .7273633 2.39 0.017 .3147587 3.16597 6 \| -.0393111 .9667391 -0.04 0.968 -1.934085 1.855463 7 \| -.2597284 .422492 -0.61 0.539 -1.087797 .5683407 8 \| .2464017 .3753992 0.66 0.512 -.4893672 .9821706 9 \| .4398809 .3360071 1.31 0.190 -.2186809 1.098443 10 \| .3974267 .3894363 1.02 0.307 -.3658545 1.160708 11 \| .7988205 .3706174 2.16 0.031 .0724237 1.525217 12 \| -.0046464 .4289148 -0.01 0.991 -.8453041 .8360112 13 \| .4774205 .3502264 1.36 0.173 -.2090105 1.163852 14 \| .5561059 .3787608 1.47 0.142 -.1862516 1.298463 15 \| .3864028 .3752701 1.03 0.303 -.3491131 1.121919 16 \| .7829345 .4034111 1.94 0.052 -.0077367 1.573606 17 \| 1.117616 .3288304 3.40 0.001 .4731205 1.762112 18 \| .6331085 .3601299 1.76 0.079 -.0727332 1.33895 19 \| .0715211 .3686188 0.19 0.846 -.6509584 .7940006 20 \| .8428357 .5836691 1.44 0.149 -.3011347 1.986806 22 \| .6743445 .3491103 1.93 0.053 -.009899 1.358588 23 \| -.0854744 .4047588 -0.21 0.833 -.8787871 .7078383 24 \| .3523933 .3844433 0.92 0.359 -.4011018 1.105888 25 \| .4547123 .3595614 1.26 0.206 -.2500151 1.15944 \| experience~g \| .0149618 .0331977 0.45 0.652 -.0501045 .080028 experience~q \| -.0633345 .1244869 -0.51 0.611 -.3073244 .1806553 share_top_~s \| .1885915 .1982024 0.95 0.341 -.1998779 .577061 share_top_~d \| .0203048 .186255 0.11 0.913 -.3447482 .3853579 \| ireport \| 3 \| .2571571 .1830048 1.41 0.160 -.1015257 .6158398 4 \| 0 (omitted) \| authored_s~o \| .128888 .175336 0.74 0.462 -.2147643 .4725402 share_fema~s \| -.4534533 .1798909 -2.52 0.012 -.8060329 -.1008737 editor_pre~t \| .0492618 .1660957 0.30 0.767 -.2762799 .3748034 _cons \| -.6916964 .440737 -1.57 0.117 -1.555525 .1721324 ------------------------------------------------------------------------------ .
▼	220	`eststo : margins, dydx() post` . eststo : margins, dydx() post Average marginal effects Number of obs = 1,079 Model VCE: Robust Expression: Pr(sign_1pct), predict() dy/dx wrt: DID IV RDD 2018.year 2.unique_j 3.unique_j 4.unique_j 5.unique_j 6.unique_j 7.unique_j 8.unique_j 9.unique_j 10.unique_j 11.unique_j 12.unique_j 13.unique_j 14.unique_j 15.unique_j 16.unique_j 17.unique_j 18.unique_j 19.unique_j 20.unique_j 22.unique_j 23.unique_j 24.unique_j 25.unique_j experience_avg experience_avg_sq share_top_authors share_top_phd 3.ireport 4.ireport authored_solo share_female_authors editor_present ------------------------------------------------------------------------------ \| Delta-method \| dy/dx std. err. z P>\|z\| [95% conf. interval] -------------+---------------------------------------------------------------- DID \| -.0633719 .0630006 -1.01 0.314 -.1868508 .0601071 IV \| -.0121923 .0601269 -0.20 0.839 -.1300389 .1056544 RDD \| -.1299814 .0976794 -1.33 0.183 -.3214294 .0614667 \| year \| 2018 \| . (not estimable) \| unique_j \| 2 \| . (not estimable) 3 \| . (not estimable) 4 \| . (not estimable) 5 \| . (not estimable) 6 \| . (not estimable) 7 \| . (not estimable) 8 \| . (not estimable) 9 \| . (not estimable) 10 \| . (not estimable) 11 \| . (not estimable) 12 \| . (not estimable) 13 \| . (not estimable) 14 \| . (not estimable) 15 \| . (not estimable) 16 \| . (not estimable) 17 \| . (not estimable) 18 \| . (not estimable) 19 \| . (not estimable) 20 \| . (not estimable) 22 \| . (not estimable) 23 \| . (not estimable) 24 \| . (not estimable) 25 \| . (not estimable) \| experience~g \| .0055573 .0123209 0.45 0.652 -.0185912 .0297059 experience~q \| -.0235247 .0462179 -0.51 0.611 -.11411 .0670607 share_top_~s \| .0700495 .0736536 0.95 0.342 -.0743089 .214408 share_top_~d \| .0075419 .0691589 0.11 0.913 -.128007 .1430909 \| ireport \| 3 \| . (not estimable) 4 \| . (not estimable) \| authored_s~o \| .0478735 .0649058 0.74 0.461 -.0793395 .1750866 share_fema~s \| -.1684285 .0656553 -2.57 0.010 -.2971105 -.0397464 editor_pre~t \| .0182975 .0616811 0.30 0.767 -.1025951 .1391902 ------------------------------------------------------------------------------ Note: dy/dx for factor levels is the discrete change from the base level. (est6 stored) .
▼	221	estadd local Window "[`threshold'$\pm$0.20]" estadd local Window "[2.58$\pm$0.20]" . estadd local Window "[`threshold'$\pm$0.20]" added macro: e(Window) : "[2.58$\pm$0.20]" .
▼	222	sum `depvar' if t>(`threshold'-0.2) & t<(`threshold'+0.2) & method=="RCT" sum sign_1pct if t>(2.58-0.2) & t<(2.58+0.2) & method=="RCT" . sum `depvar' if t>(`threshold'-0.2) & t<(`threshold'+0.2) > & method=="RCT" Variable \| Obs Mean Std. dev. Min Max -------------+--------------------------------------------------------- sign_1pct \| 301 .461794 .4993684 0 1 .
▼	223	`estadd local rct_sign = round(r(mean), 0.01)` `. estadd local rct_sign = round(r(mean), 0.01) added macro: e(rct_sign) : ".46" .`
	224
▼	225	`esttab, margin ///` esttab, margin keep(DID IV RDD top5 2018.year experience_avg experience_avg_sq share_top_authors share_top_phd ) label stats(N Window rct_sign, fmt(%9.0fc) labels("Observations" "Window" "RCT sig rate")) . esttab, margin keep(DID IV RDD top5 2018.year experience_a > vg experience_avg_sq share_top_authors share_top_phd ) label stats(N Window r > ct_sign, fmt(%9.0fc) labels("Observations" "Window" "RCT sig rate")) ------------------------------------------------------------------------------- > ------------------------------------- (1) (2) (3) ( > 4) (5) (6) > ------------------------------------------------------------------------------- > ------------------------------------- DID 0.0500 0.0402 0.0214 0.009 > 57 0.0263 -0.0634 (1.03) (0.89) (0.45) (0.2 > 0) (0.48) (-1.01) IV 0.0194 0.00871 -0.0174 -0.03 > 94 -0.0184 -0.0122 (0.46) (0.22) (-0.43) (-0.9 > 5) (-0.40) (-0.20) RDD -0.0821 -0.0825 -0.0935 -0.09 > 18 -0.0760 -0.130 (-1.21) (-1.33) (-1.51) (-1.4 > 2) (-1.06) (-1.33) Top 5 0.0287 -0.101 > (0.52) (-1.00) > Year=2018 0.0102 0.00843 0.02 > 19 0 0 (0.25) (0.20) (0.5 > 3) (.) (.) Experience 0.0180 0.0161 0.01 > 31 0.0140 0.00556 (1.91) (1.78) (1.4 > 7) (1.33) (0.45) Experience squared -0.0494 -0.0437 -0.03 > 74 -0.0426 -0.0235 (-1.64) (-1.51) (-1.3 > 3) (-1.09) (-0.51) Top institution 0.00318 0.00641 0.006 > 22 0.000590 0.0700 (0.05) (0.10) (0.1 > 0) (0.01) (0.95) Top PhD institution -0.0511 -0.0526 -0.03 > 79 0.0256 0.00754 (-0.96) (-0.98) (-0.6 > 8) (0.40) (0.11) ------------------------------------------------------------------------------- > ------------------------------------- Observations 2,689 2,689 2,689 2,6 > 89 1,850 1,079 Window [2.58$\pm$0.50] [2.58$\pm$0.50] [2.58$\pm$0.50] [ > 2.58$\pm$0.50] [2.58$\pm$0.35] [2.58$\pm$0.20] RCT sig rate .37 .37 .37 . > 37 .42 .46 ------------------------------------------------------------------------------- > ------------------------------------- Marginal effects; t statistics in parentheses (d) for discrete change of dummy variable from 0 to 1 * p<0.05, p<0.01, * p<0.001 .
	226	`keep(DID IV RDD top5 2018.year experience_avg experience_avg_sq share_top_authors share_top_phd ) label stats(N Window rct_sign, fmt(%9.0fc) labels("Observations" "Window" "RCT sig rate"))`
	227
▼	228	esttab using table_A6_caliper_`depvar'.tex, margin /// esttab using table_A6_caliper_sign_1pct.tex, margin keep(DID IV RDD top5 2018.year experience_avg experience_avg_sq share_top_authors share_top_phd) label stats(N Window rct_sign, fmt(%9.0fc) labels("Observations" "Window" "RCT sig rate")) mtitles() nomtitles nostar compress se(3) b(3) replace nogaps noomitted indicate( "Reporting Method = ireport" "Solo Authored = authored_solo" "Share Female Authors = share_female_authors" "Editor = editor_present" "Field FE = FINANCE" "Journal FE = unique_j" , labels("Y" " ")) nonotes . esttab using "table_A6_caliper_sign_1pct.tex", margin keep(DID IV > RDD top5 2018.year experience_avg experience_avg_sq share_top_authors share_t > op_phd) label stats(N Window rct_sign, fmt(%9.0fc) labels("Observations" "Wi > ndow" "RCT sig rate")) mtitles() nomtitles nostar compress se(3) b(3) replace > nogaps noomitted indicate( "Reporting Method = ireport" "Solo Authored = au > thored_solo" "Share Female Authors = share_female_authors" "Editor = editor_p > resent" "Field FE = FINANCE" "Journal FE = unique_j" , labels("Y" " ")) nono > tes (output written to table_A6_caliper_sign_1pct.tex) .
	229	`keep(DID IV RDD top5 2018.year experience_avg experience_avg_sq share_top_authors share_top_phd) label stats(N Window rct_sign, fmt(%9.0fc) labels("Observations" "Window" "RCT sig rate")) ///`
	230	`mtitles() nomtitles nostar ///`
	231	`compress se(3) b(3) replace nogaps noomitted ///`
	232	`indicate( ///`
	233	`"Reporting Method = *ireport" ///`
	234	`"Solo Authored = authored_solo" ///`
	235	`"Share Female Authors = share_female_authors" ///`
	236	`"Editor = editor_present" ///`
	237	`"Field FE = FINANCE" ///`
	238	`"Journal FE = *unique_j" ///`
	239	`, labels("Y" " ")) ///`
	240	`nonotes`
	241
	242
	243
	244

	1	`/* This file was run to create the ado folder, but does not need to be run given the ado folder exists */`
	2	`/* setup.do */`
▼	3	`sysdir` `. sysdir STATA: /usr/local/stata/ BASE: /usr/local/stata/ado/base/ SITE: /usr/local/ado/ PLUS: ~/ado/plus/ PERSONAL: ~/ado/personal/ OLDPLACE: ~/ado/ .`
	4
	5	`/* add packages to the macro */`
	6
	7	`* * Add required packages from SSC to this list *`
▼	8	`local ssc_packages "estout egenmore"` `. local ssc_packages "estout egenmore" .`
	9
	10	`// local ssc_packages "estout boottest"`
	11
	12	if !missing("`ssc_packages'") {
▼	13	foreach pkg in `ssc_packages' { `foreach pkg in estout egenmore {`
▼	14	dis "Installing `pkg'" Run 1 Run 2 `dis "Installing estout" Installing estout` `dis "Installing egenmore" Installing egenmore`
	15	ssc install `pkg', replace
	16	`}`
	17	`}`
	18
	19	`* Install packages using net`
	20	`* net install yaml, from("https://raw.githubusercontent.com/gslab-econ/stata-misc/master/")`
	21
	22	`/* other commands */`
	23
	24	`/* after installing all packages, it may be necessary to issue the mata mlib index command */`
▼	25	`mata: mata mlib index` . mata: mata mlib index .mlib libraries to be searched are now lmatabase;lmatamcmc;lmatafc;lmatapss;lmatasem;lmatasp;lmatabma;lmatasvy;lma > tacollect;lmataerm;lmatatab;lmatami;lmatalasso;lmataado;lmatamixlog;lmataopt; > lmatagsem;lmatameta;lmatapostest;lmatanumlib;lmatapath;lnwspgr;lintegrate;lxt > spj;lout;lsplagvar;lmetapreg;lepimodels;lcureregr_lf;lusexmlex;lfieldarea;lst > ns;lmultistate;lxtabond2;lgo;ltolong;lplssem;lspwmatrix;lxtbreak;lskolenik;ls > qbm;lasdoc;ltestcase;lcmc;lsomersd;lgeochart;lxtdpdqml;lstjm;ltoxl_v13;lasreg > ;lstpm2;lmcmclinear;lmoremata;lratetable;lasgen;linorm;leefanalytics;licio;lq > env9;lboottest;lnearstat;lmargdistfit;lcem;lpoparms;lhetsar;lsynth_mata_subr; > lsetpoisson;lcolrspace;ligencox;librecycle;lsmwoodbury;lirand;ltihtest11;lghk > 2;lalogit;lkinkyreg;lkhb;lelabel;lasrol;lstandsurv;lqenv10;lsfpanel;lpanelhet > ero;lmoremata11;ltoxl_v14;lquaidsce;lparallel;lasn;lpsweight;lextreme;lrcl;ls > kolenik10;lmmtxttool;lxtdpdgmm;lspmat;libjson;lfrcount;lgetsymbols;lmetadta;l > kdens;lmhtreg;lsq;lstaft;lmatrixtools;lbasetable;ltihtest13;lmetan;lftools;lr > pn;lsbmeff;lgtools;lsae_povmap;lstmt;lsfcross;llog2markup;lsavespss;lfreduse; > ltihtest12;ludiff;lmerlin;lxtseqreg;lcmp;lportheory;lmoremata10;l_cfrmt;lpetp > oisson;lstrcs;livreg2;lguttmanl;lmhtexp;lsls;lsmclpres;lmoremata14;lxtivdfreg > ;lflexmat;lxsmle;larimaauto;luse13 .
	26
	27
▼	28	`set more off, perm` `. set more off, perm (set more preference recorded) .`
	29
	30

	1	`*** This script generates Figures 3,4,5, A1 and A2 in our comment which are replications of BCH's Figures 1,2,3,5 and 6 (BCH's Figure 4 is replicated using R)`
	2
▼	3	`clear` `. clear .`
▼	4	`set more off` `. set more off .`
	5
	6	`* specify directories where data are located and where results should be stored`
▼	7	`global dir_main : pwd` `. global dir_main : pwd .`
▼	8	`global dir_data "$dir_main/Data"` `global dir_data "/home/rstudio/repbox/projects_ejd/aer_112_9_9/mod/Scripts/Data" . global dir_data "$dir_main/Data" .`
▼	9	`global dir_results "$dir_main/Results"` `global dir_results "/home/rstudio/repbox/projects_ejd/aer_112_9_9/mod/Scripts/Results" . global dir_results "$dir_main/Results" .`
	10
	11	`* read in the data`
▼	12	`cd "$dir_data"` `cd "/home/rstudio/repbox/projects_ejd/aer_112_9_9/mod/Scripts/Data" . cd "${repbox_path}/Data" /home/rstudio/repbox/projects_ejd/aer_112_9_9/mod/Data .`
▼	13	`capture use "MM_new.dta", clear` `. capture use "MM_new.dta", clear .`
	14
	15	`* set folder to store results`
▼	16	`cd "$dir_results"` `cd "/home/rstudio/repbox/projects_ejd/aer_112_9_9/mod/Scripts/Results" . cd "${repbox_path}/Results" /home/rstudio/repbox/projects_ejd/aer_112_9_9/mod/Results .`
	17
	18	`*** Figure 3 in our comment`
▼	19	`histogram t if t <= 10 & keep_obs==1, saving(temp1, replace) title() width(0.1) start(0) fcolor(gs10) lcolor(gs10) kdensity kdenopts(width(0.1)) xtitle(z-statistic, size(large)) ytitle(Density, size(large)) xline(1.65 1.96 2.58, lwidth(thin)) xlabel(0(1)10, labels labsize(large)) ylabel(, labels labsize(large)) legend(off) scheme(s1mono) addplot((kdensity t if t <= 10, bwidth(0.1) lpattern(vshortdash) lcolor(black) ))` histogram t if t <= 10 & keep_obs==1, saving(temp1, replace) title() width(0.1) start(0) fcolor(gs10) lcolor(gs10) kdensity kdenopts(width(0.1)) xtitle(z-statistic, size(large)) ytitle(Density, size(large)) xline(1.65 1.96 2.58, lwidth(thin)) xlabel(0(1)10, labels labsize(large)) ylabel(, labels labsize(large)) legend(off) scheme(s1mono) addplot((kdensity t if t <= 10, bwidth(0.1) lpattern(vshortdash) lcolor(black) )) . histogram t if t <= 10 & keep_obs==1, saving("`r(repbox_fo > und_file)'", replace) title() width(0.1) start(0) fcolor(gs10) lcolor(gs10) k > density kdenopts(width(0.1)) xtitle(z-statistic, size(large)) ytitle(Density, > size(large)) xline(1.65 1.96 2.58, lwidth(thin)) xlabel(0(1)10, labels labs > ize(large)) ylabel(, labels labsize(large)) legend(off) scheme(s1mono) addplo > t((kdensity t if t <= 10, bwidth(0.1) lpattern(vshortdash) lcolor(black) )) (bin=100, start=0, width=.1) (file temp1.gph not found) file temp1.gph saved .
▼	20	`graph export figure_3a.pdf, replace` `graph export figure_3a.pdf, replace . graph export "figure_3a.pdf", replace file figure_3a.pdf saved as PDF format .`
	21
▼	22	`histogram t if t <= 10 & top5==1 & keep_obs==1, title("Top 5") saving(temp2, replace) width(0.1) start(0) fcolor(gs10) lcolor(gs10) kdensity kdenopts(width(0.1)) xtitle(z-statistic, size(large)) ytitle(Density, size(large)) xline(1.65 1.96 2.58, lwidth(thin)) xlabel(0(1)10, labels labsize(large)) ylabel(, labels labsize(large)) legend(off) scheme(s1mono) addplot((kdensity t if t <= 10 & top5==1 , bwidth(0.1) lpattern(vshortdash) lcolor(black) ))` histogram t if t <= 10 & top5==1 & keep_obs==1, title("Top 5") saving(temp2, replace) width(0.1) start(0) fcolor(gs10) lcolor(gs10) kdensity kdenopts(width(0.1)) xtitle(z-statistic, size(large)) ytitle(Density, size(large)) xline(1.65 1.96 2.58, lwidth(thin)) xlabel(0(1)10, labels labsize(large)) ylabel(, labels labsize(large)) legend(off) scheme(s1mono) addplot((kdensity t if t <= 10 & top5==1 , bwidth(0.1) lpattern(vshortdash) lcolor(black) )) . histogram t if t <= 10 & top5==1 & keep_obs==1, title("Top > 5") saving("temp2", replace) width(0.1) start(0) fcolor(gs1 > 0) lcolor(gs10) kdensity kdenopts(width(0.1)) xtitle(z-statistic, size(large) > ) ytitle(Density, size(large)) xline(1.65 1.96 2.58, lwidth(thin)) xlabel(0( > 1)10, labels labsize(large)) ylabel(, labels labsize(large)) legend(off) sche > me(s1mono) addplot((kdensity t if t <= 10 & top5==1 , bwidth(0.1) lpattern(vs > hortdash) lcolor(black) )) (bin=100, start=0, width=.1) (file temp2.gph not found) file temp2.gph saved .
▼	23	`graph export figure_3b.pdf, replace` `graph export figure_3b.pdf, replace . graph export "figure_3b.pdf", replace file figure_3b.pdf saved as PDF format .`
	24
▼	25	`histogram t if t <= 10 & top5==0 & keep_obs==1, title("Non-Top 5") saving(temp3, replace) width(0.1) start(0) fcolor(gs10) lcolor(gs10) kdensity kdenopts(width(0.1)) xtitle(z-statistic, size(large)) ytitle(Density, size(large)) xline(1.65 1.96 2.58, lwidth(thin)) xlabel(0(1)10, labels labsize(large)) ylabel(, labels labsize(large)) legend(off) scheme(s1mono) addplot((kdensity t if t <= 10 & top5==0, bwidth(0.1) lpattern(vshortdash) lcolor(black) ))` histogram t if t <= 10 & top5==0 & keep_obs==1, title("Non-Top 5") saving(temp3, replace) width(0.1) start(0) fcolor(gs10) lcolor(gs10) kdensity kdenopts(width(0.1)) xtitle(z-statistic, size(large)) ytitle(Density, size(large)) xline(1.65 1.96 2.58, lwidth(thin)) xlabel(0(1)10, labels labsize(large)) ylabel(, labels labsize(large)) legend(off) scheme(s1mono) addplot((kdensity t if t <= 10 & top5==0, bwidth(0.1) lpattern(vshortdash) lcolor(black) )) . histogram t if t <= 10 & top5==0 & keep_obs==1, title("Non > -Top 5") saving("temp3", replace) width(0.1) start(0) fcolor > (gs10) lcolor(gs10) kdensity kdenopts(width(0.1)) xtitle(z-statistic, size(la > rge)) ytitle(Density, size(large)) xline(1.65 1.96 2.58, lwidth(thin)) xlabe > l(0(1)10, labels labsize(large)) ylabel(, labels labsize(large)) legend(off) > scheme(s1mono) addplot((kdensity t if t <= 10 & top5==0, bwidth(0.1) lpattern > (vshortdash) lcolor(black) )) (bin=100, start=0, width=.1) (file temp3.gph not found) file temp3.gph saved .
▼	26	`graph export figure_3c.pdf, replace` `graph export figure_3c.pdf, replace . graph export "figure_3c.pdf", replace file figure_3c.pdf saved as PDF format .`
	27
	28
	29	`*** Figure 4 in our comment`
	30
▼	31	`histogram t if t <= 10 & method=="DID" & keep_obs==1 , title("DID") saving(temp1, replace) width(0.1) start(0) fcolor(gs10) lcolor(gs10) kdensity kdenopts(width(0.1)) xtitle(z-statistic, size(large)) ytitle(Density, size(large)) xline(1.65 1.96 2.58, lwidth(thin)) xlabel(0(1)10, labels labsize(large)) ylabel(, labels labsize(large)) legend(off) scheme(s1mono) addplot((kdensity t if t <= 10 & method=="DID", bwidth(0.1) lpattern(vshortdash) lcolor(black) ))` histogram t if t <= 10 & method=="DID" & keep_obs==1 , title("DID") saving(temp1, replace) width(0.1) start(0) fcolor(gs10) lcolor(gs10) kdensity kdenopts(width(0.1)) xtitle(z-statistic, size(large)) ytitle(Density, size(large)) xline(1.65 1.96 2.58, lwidth(thin)) xlabel(0(1)10, labels labsize(large)) ylabel(, labels labsize(large)) legend(off) scheme(s1mono) addplot((kdensity t if t <= 10 & method=="DID", bwidth(0.1) lpattern(vshortdash) lcolor(black) )) . histogram t if t <= 10 & method=="DID" & keep_obs==1 , tit > le("DID") saving("temp1", replace) width(0.1) start(0) fcolo > r(gs10) lcolor(gs10) kdensity kdenopts(width(0.1)) xtitle(z-statistic, size(l > arge)) ytitle(Density, size(large)) xline(1.65 1.96 2.58, lwidth(thin)) xlabe > l(0(1)10, labels labsize(large)) ylabel(, labels labsize(large)) legend(off) > scheme(s1mono) addplot((kdensity t if t <= 10 & method=="DID", bwidth(0.1) lp > attern(vshortdash) lcolor(black) )) (bin=100, start=0, width=.1) file temp1.gph saved .
▼	32	`graph export figure_4_did.pdf, replace` `graph export figure_4_did.pdf, replace . graph export "figure_4_did.pdf", replace file figure_4_did.pdf saved as PDF format .`
▼	33	`histogram t if t <= 10 & method=="IV" & keep_obs==1 , title("IV") saving(temp1, replace) width(0.1) start(0) fcolor(gs10) lcolor(gs10) kdensity kdenopts(width(0.1)) xtitle(z-statistic, size(large)) ytitle(Density, size(large)) xline(1.65 1.96 2.58, lwidth(thin)) xlabel(0(1)10, labels labsize(large)) ylabel(, labels labsize(large)) legend(off) scheme(s1mono) addplot((kdensity t if t <= 10 & method=="IV", bwidth(0.1) lpattern(vshortdash) lcolor(black) ))` histogram t if t <= 10 & method=="IV" & keep_obs==1 , title("IV") saving(temp1, replace) width(0.1) start(0) fcolor(gs10) lcolor(gs10) kdensity kdenopts(width(0.1)) xtitle(z-statistic, size(large)) ytitle(Density, size(large)) xline(1.65 1.96 2.58, lwidth(thin)) xlabel(0(1)10, labels labsize(large)) ylabel(, labels labsize(large)) legend(off) scheme(s1mono) addplot((kdensity t if t <= 10 & method=="IV", bwidth(0.1) lpattern(vshortdash) lcolor(black) )) . histogram t if t <= 10 & method=="IV" & keep_obs==1 , titl > e("IV") saving("temp1", replace) width(0.1) start(0) fcolor( > gs10) lcolor(gs10) kdensity kdenopts(width(0.1)) xtitle(z-statistic, size(lar > ge)) ytitle(Density, size(large)) xline(1.65 1.96 2.58, lwidth(thin)) xlabel( > 0(1)10, labels labsize(large)) ylabel(, labels labsize(large)) legend(off) sc > heme(s1mono) addplot((kdensity t if t <= 10 & method=="IV", bwidth(0.1) lpatt > ern(vshortdash) lcolor(black) )) (bin=100, start=0, width=.1) file temp1.gph saved .
▼	34	`graph export figure_4_iv.pdf, replace` `graph export figure_4_iv.pdf, replace . graph export "figure_4_iv.pdf", replace file figure_4_iv.pdf saved as PDF format .`
▼	35	`histogram t if t <= 10 & method=="RCT" & keep_obs==1 , title("RCT") saving(temp1, replace) width(0.1) start(0) fcolor(gs10) lcolor(gs10) kdensity kdenopts(width(0.1)) xtitle(z-statistic, size(large)) ytitle(Density, size(large)) xline(1.65 1.96 2.58, lwidth(thin)) xlabel(0(1)10, labels labsize(large)) ylabel(, labels labsize(large)) legend(off) scheme(s1mono) addplot((kdensity t if t <= 10 & method=="RCT", bwidth(0.1) lpattern(vshortdash) lcolor(black) ))` histogram t if t <= 10 & method=="RCT" & keep_obs==1 , title("RCT") saving(temp1, replace) width(0.1) start(0) fcolor(gs10) lcolor(gs10) kdensity kdenopts(width(0.1)) xtitle(z-statistic, size(large)) ytitle(Density, size(large)) xline(1.65 1.96 2.58, lwidth(thin)) xlabel(0(1)10, labels labsize(large)) ylabel(, labels labsize(large)) legend(off) scheme(s1mono) addplot((kdensity t if t <= 10 & method=="RCT", bwidth(0.1) lpattern(vshortdash) lcolor(black) )) . histogram t if t <= 10 & method=="RCT" & keep_obs==1 , tit > le("RCT") saving("temp1", replace) width(0.1) start(0) fcolo > r(gs10) lcolor(gs10) kdensity kdenopts(width(0.1)) xtitle(z-statistic, size(l > arge)) ytitle(Density, size(large)) xline(1.65 1.96 2.58, lwidth(thin)) xlabe > l(0(1)10, labels labsize(large)) ylabel(, labels labsize(large)) legend(off) > scheme(s1mono) addplot((kdensity t if t <= 10 & method=="RCT", bwidth(0.1) lp > attern(vshortdash) lcolor(black) )) (bin=100, start=0, width=.1) file temp1.gph saved .
▼	36	`graph export figure_4_rct.pdf, replace` `graph export figure_4_rct.pdf, replace . graph export "figure_4_rct.pdf", replace file figure_4_rct.pdf saved as PDF format .`
▼	37	`histogram t if t <= 10 & method=="RDD" & keep_obs==1 , title("RDD") saving(temp1, replace) width(0.1) start(0) fcolor(gs10) lcolor(gs10) kdensity kdenopts(width(0.1)) xtitle(z-statistic, size(large)) ytitle(Density, size(large)) xline(1.65 1.96 2.58, lwidth(thin)) xlabel(0(1)10, labels labsize(large)) ylabel(, labels labsize(large)) legend(off) scheme(s1mono) addplot((kdensity t if t <= 10 & method=="RDD", bwidth(0.1) lpattern(vshortdash) lcolor(black) ))` histogram t if t <= 10 & method=="RDD" & keep_obs==1 , title("RDD") saving(temp1, replace) width(0.1) start(0) fcolor(gs10) lcolor(gs10) kdensity kdenopts(width(0.1)) xtitle(z-statistic, size(large)) ytitle(Density, size(large)) xline(1.65 1.96 2.58, lwidth(thin)) xlabel(0(1)10, labels labsize(large)) ylabel(, labels labsize(large)) legend(off) scheme(s1mono) addplot((kdensity t if t <= 10 & method=="RDD", bwidth(0.1) lpattern(vshortdash) lcolor(black) )) . histogram t if t <= 10 & method=="RDD" & keep_obs==1 , tit > le("RDD") saving("temp1", replace) width(0.1) start(0) fcolo > r(gs10) lcolor(gs10) kdensity kdenopts(width(0.1)) xtitle(z-statistic, size(l > arge)) ytitle(Density, size(large)) xline(1.65 1.96 2.58, lwidth(thin)) xlabe > l(0(1)10, labels labsize(large)) ylabel(, labels labsize(large)) legend(off) > scheme(s1mono) addplot((kdensity t if t <= 10 & method=="RDD", bwidth(0.1) lp > attern(vshortdash) lcolor(black) )) (bin=99, start=0, width=.1) file temp1.gph saved .
▼	38	`graph export figure_4_rdd.pdf, replace` `graph export figure_4_rdd.pdf, replace . graph export "figure_4_rdd.pdf", replace file figure_4_rdd.pdf saved as PDF format .`
	39
	40
	41	`*** Figure 5 in our comment`
	42	`*** Note that we used an approximate merging procedure to get the standard errors for the`
	43	`*** Star Wars data`
	44
▼	45	`clear all` `. clear all .`
▼	46	`set more off` `. set more off .`
	47	`* read in the data`
▼	48	`cd "$dir_data"` `cd "/home/rstudio/repbox/projects_ejd/aer_112_9_9/mod/Scripts/Data" . cd "${repbox_path}/Data" /home/rstudio/repbox/projects_ejd/aer_112_9_9/mod/Data .`
	49
▼	50	`use "starwars_bch_pk.dta", clear` `. use "starwars_bch_pk.dta", clear .`
▼	51	`rename journal journal_name` `. rename journal journal_name .`
	52
▼	53	`append using "MM_new.dta", force` `. append using "MM_new.dta", force (variable journal_name was str30, now str44 to accommodate using data's values) (variable mu_str was str12, now str19 to accommodate using data's values) .`
	54
	55	`* determine folder to store results`
▼	56	`cd "$dir_results"` `cd "/home/rstudio/repbox/projects_ejd/aer_112_9_9/mod/Scripts/Results" . cd "${repbox_path}/Results" /home/rstudio/repbox/projects_ejd/aer_112_9_9/mod/Results .`
	57
▼	58	`capture drop top3` `. capture drop top3 .`
	59
▼	60	`gen top3 = 0` `. gen top3 = 0 .`
▼	61	`replace top3 = 1 if strpos(journal_name,"Quarterly Journal of Economics")` `replace top3 = 1 if strpos(journal_name,"Quarterly Journal of Economics") . replace top3 = 1 if strpos(journal_name,"Quarterly Journal > of Economics") (7,920 real changes made) .`
▼	62	`replace top3 = 1 if strpos(journal_name,"Journal of Political Economy")` `replace top3 = 1 if strpos(journal_name,"Journal of Political Economy") . replace top3 = 1 if strpos(journal_name,"Journal of Politi > cal Economy") (3,480 real changes made) .`
▼	63	`replace top3 = 1 if strpos(journal_name,"American Economic Review")` `replace top3 = 1 if strpos(journal_name,"American Economic Review") . replace top3 = 1 if strpos(journal_name,"American Economic > Review") (9,824 real changes made) .`
	64
▼	65	`histogram t if keep_obs==1 & t <= 10 & year<2015 & top3==1 , title("2005-2011") saving(temp1, replace) width(0.1) start(0) fcolor(gs10) lcolor(gs10) kdensity kdenopts(width(0.1)) xtitle(z-statistic, size(large)) ytitle(Density, size(large)) xline(1.65 1.96 2.58, lwidth(thin)) xlabel(0(1)10, labels labsize(large)) ylabel(, labels labsize(large)) legend(off) scheme(s1mono) addplot((kdensity t if t <= 10 & year<2015 & top3==1, bwidth(0.1) lpattern(vshortdash) lcolor(black) ))` histogram t if keep_obs==1 & t <= 10 & year<2015 & top3==1 , title("2005-2011") saving(temp1, replace) width(0.1) start(0) fcolor(gs10) lcolor(gs10) kdensity kdenopts(width(0.1)) xtitle(z-statistic, size(large)) ytitle(Density, size(large)) xline(1.65 1.96 2.58, lwidth(thin)) xlabel(0(1)10, labels labsize(large)) ylabel(, labels labsize(large)) legend(off) scheme(s1mono) addplot((kdensity t if t <= 10 & year<2015 & top3==1, bwidth(0.1) lpattern(vshortdash) lcolor(black) )) . histogram t if keep_obs==1 & t <= 10 & year<2015 & top3==1 > , title("2005-2011") saving("temp1", replace) width(0.1) st > art(0) fcolor(gs10) lcolor(gs10) kdensity kdenopts(width(0.1)) xtitle(z-stati > stic, size(large)) ytitle(Density, size(large)) xline(1.65 1.96 2.58, lwidth( > thin)) xlabel(0(1)10, labels labsize(large)) ylabel(, labels labsize(large)) > legend(off) scheme(s1mono) addplot((kdensity t if t <= 10 & year<2015 & top3= > =1, bwidth(0.1) lpattern(vshortdash) lcolor(black) )) (bin=100, start=0, width=.1) file temp1.gph saved .
▼	66	`graph export figure_5a.pdf, replace` `graph export figure_5a.pdf, replace . graph export "figure_5a.pdf", replace file figure_5a.pdf saved as PDF format .`
▼	67	`histogram t if keep_obs==1 & t <= 10 & year>=2015 & top3==1 , title("2015 & 2018") saving(temp2, replace) width(0.1) start(0) fcolor(gs10) lcolor(gs10) kdensity kdenopts(width(0.1)) xtitle(z-statistic, size(large)) ytitle(Density, size(large)) xline(1.65 1.96 2.58, lwidth(thin)) xlabel(0(1)10, labels labsize(large)) ylabel(, labels labsize(large)) legend(off) scheme(s1mono) addplot((kdensity t if t <= 10 & year>=2015 & top3==1, bwidth(0.1) lpattern(vshortdash) lcolor(black) ))` histogram t if keep_obs==1 & t <= 10 & year>=2015 & top3==1 , title("2015 & 2018") saving(temp2, replace) width(0.1) start(0) fcolor(gs10) lcolor(gs10) kdensity kdenopts(width(0.1)) xtitle(z-statistic, size(large)) ytitle(Density, size(large)) xline(1.65 1.96 2.58, lwidth(thin)) xlabel(0(1)10, labels labsize(large)) ylabel(, labels labsize(large)) legend(off) scheme(s1mono) addplot((kdensity t if t <= 10 & year>=2015 & top3==1, bwidth(0.1) lpattern(vshortdash) lcolor(black) )) . histogram t if keep_obs==1 & t <= 10 & year>=2015 & top3= > =1 , title("2015 & 2018") saving("temp2", replace) width(0.1 > ) start(0) fcolor(gs10) lcolor(gs10) kdensity kdenopts(width(0.1)) xtitle(z-s > tatistic, size(large)) ytitle(Density, size(large)) xline(1.65 1.96 2.58, lwi > dth(thin)) xlabel(0(1)10, labels labsize(large)) ylabel(, labels labsize(larg > e)) legend(off) scheme(s1mono) addplot((kdensity t if t <= 10 & year>=2015 & > top3==1, bwidth(0.1) lpattern(vshortdash) lcolor(black) )) (bin=100, start=0, width=.1) file temp2.gph saved .
▼	68	`graph export figure_5b.pdf, replace` `graph export figure_5b.pdf, replace . graph export "figure_5b.pdf", replace file figure_5b.pdf saved as PDF format .`
	69
	70	`* read in the data`
▼	71	`cd "$dir_data"` `cd "/home/rstudio/repbox/projects_ejd/aer_112_9_9/mod/Scripts/Data" . cd "${repbox_path}/Data" /home/rstudio/repbox/projects_ejd/aer_112_9_9/mod/Data .`
▼	72	`capture use "MM_new.dta", clear` `. capture use "MM_new.dta", clear .`
	73
	74	`* determine folder to store results`
▼	75	`cd "$dir_results"` `cd "/home/rstudio/repbox/projects_ejd/aer_112_9_9/mod/Scripts/Results" . cd "${repbox_path}/Results" /home/rstudio/repbox/projects_ejd/aer_112_9_9/mod/Results .`
	76
▼	77	`histogram t if keep_obs==1 & t <= 10 & year==2015 , title("2015") saving(temp3, replace) width(0.1) start(0) fcolor(gs10) lcolor(gs10) kdensity kdenopts(width(0.1)) xtitle(z-statistic, size(large)) ytitle(Density, size(large)) xline(1.65 1.96 2.58, lwidth(thin)) xlabel(0(1)10, labels labsize(large)) ylabel(, labels labsize(large)) legend(off) scheme(s1mono) addplot((kdensity t if t <= 10 & year==2015 , bwidth(0.1) lpattern(vshortdash) lcolor(black) ))` histogram t if keep_obs==1 & t <= 10 & year==2015 , title("2015") saving(temp3, replace) width(0.1) start(0) fcolor(gs10) lcolor(gs10) kdensity kdenopts(width(0.1)) xtitle(z-statistic, size(large)) ytitle(Density, size(large)) xline(1.65 1.96 2.58, lwidth(thin)) xlabel(0(1)10, labels labsize(large)) ylabel(, labels labsize(large)) legend(off) scheme(s1mono) addplot((kdensity t if t <= 10 & year==2015 , bwidth(0.1) lpattern(vshortdash) lcolor(black) )) . histogram t if keep_obs==1 & t <= 10 & year==2015 , title( > "2015") saving("temp3", replace) width(0.1) start(0) fcolor( > gs10) lcolor(gs10) kdensity kdenopts(width(0.1)) xtitle(z-statistic, size(lar > ge)) ytitle(Density, size(large)) xline(1.65 1.96 2.58, lwidth(thin)) xlabel( > 0(1)10, labels labsize(large)) ylabel(, labels labsize(large)) legend(off) sc > heme(s1mono) addplot((kdensity t if t <= 10 & year==2015 , bwidth(0.1) lpatte > rn(vshortdash) lcolor(black) )) (bin=100, start=0, width=.1) file temp3.gph saved .
▼	78	`graph export figure_5c.pdf, replace` `graph export figure_5c.pdf, replace . graph export "figure_5c.pdf", replace file figure_5c.pdf saved as PDF format .`
▼	79	`histogram t if keep_obs==1 & t <= 10 & year==2018 , title("2018") saving(temp4, replace) width(0.1) start(0) fcolor(gs10) lcolor(gs10) kdensity kdenopts(width(0.1)) xtitle(z-statistic, size(large)) ytitle(Density, size(large)) xline(1.65 1.96 2.58, lwidth(thin)) xlabel(0(1)10, labels labsize(large)) ylabel(, labels labsize(large)) legend(off) scheme(s1mono) addplot((kdensity t if t <= 10 & year==2018 , bwidth(0.1) lpattern(vshortdash) lcolor(black) ))` histogram t if keep_obs==1 & t <= 10 & year==2018 , title("2018") saving(temp4, replace) width(0.1) start(0) fcolor(gs10) lcolor(gs10) kdensity kdenopts(width(0.1)) xtitle(z-statistic, size(large)) ytitle(Density, size(large)) xline(1.65 1.96 2.58, lwidth(thin)) xlabel(0(1)10, labels labsize(large)) ylabel(, labels labsize(large)) legend(off) scheme(s1mono) addplot((kdensity t if t <= 10 & year==2018 , bwidth(0.1) lpattern(vshortdash) lcolor(black) )) . histogram t if keep_obs==1 & t <= 10 & year==2018 , title( > "2018") saving("temp4", replace) width(0.1) start(0) fcolor( > gs10) lcolor(gs10) kdensity kdenopts(width(0.1)) xtitle(z-statistic, size(lar > ge)) ytitle(Density, size(large)) xline(1.65 1.96 2.58, lwidth(thin)) xlabel( > 0(1)10, labels labsize(large)) ylabel(, labels labsize(large)) legend(off) sc > heme(s1mono) addplot((kdensity t if t <= 10 & year==2018 , bwidth(0.1) lpatte > rn(vshortdash) lcolor(black) )) (bin=99, start=0, width=.1) (file temp4.gph not found) file temp4.gph saved .
▼	80	`graph export figure_5d.pdf, replace` `graph export figure_5d.pdf, replace . graph export "figure_5d.pdf", replace file figure_5d.pdf saved as PDF format .`
	81
	82
	83	`*** Figure A1 in our comment`
	84	`* drop obs with small significand`
▼	85	`keep if keep_obs==1` `. keep if keep_obs==1 (8,233 observations deleted) .`
▼	86	`capture destring fstat, replace force` `. capture destring fstat, replace force .`
	87
▼	88	`histogram fstat if fstat <= 50 , title() width(2) start(0) fcolor(gs10) lcolor(gs10) kdensity kdenopts() xtitle(F-statistic, size(large)) ytitle(Density, size(large)) xline(10, lwidth(thin)) xlabel(0 10 20 30 40 50, labels labsize(large)) ylabel(, labels labsize(large)) legend(off) scheme(s1mono)` histogram fstat if fstat <= 50 , title() width(2) start(0) fcolor(gs10) lcolor(gs10) kdensity kdenopts() xtitle(F-statistic, size(large)) ytitle(Density, size(large)) xline(10, lwidth(thin)) xlabel(0 10 20 30 40 50, labels labsize(large)) ylabel(, labels labsize(large)) legend(off) scheme(s1mono) . histogram fstat if fstat <= 50 , title() width(2) start(0) > fcolor(gs10) lcolor(gs10) kdensity kdenopts() xtitle(F-statistic, size(large > )) ytitle(Density, size(large)) xline(10, lwidth(thin)) xlabel(0 10 20 30 40 > 50, labels labsize(large)) ylabel(, labels labsize(large)) legend(off) scheme > (s1mono) (bin=25, start=0, width=2) .
▼	89	`graph export figure_A1a.pdf, replace` `graph export figure_A1a.pdf, replace . graph export "figure_A1a.pdf", replace file figure_A1a.pdf saved as PDF format .`
	90
	91
▼	92	`capture destring fstat, replace force` `. capture destring fstat, replace force .`
	93
▼	94	`histogram t if t <= 10 & method=="IV" & fstat< 30 , title("F less than 30") saving(temp1, replace) width(0.1) start(0) fcolor(gs10) lcolor(gs10) kdensity kdenopts(width(0.1)) ytitle(Density, size(large)) xtitle(z-statistic, size(large)) xline(1.65 1.96 2.58, lwidth(thin)) xlabel(0 1 1.65 "" 1.96 "" 2.58 "*" 3 4 5 6 7 8 9 10, labels labsize(large)) ylabel(, labels labsize(large)) legend(off) scheme(s1mono)` histogram t if t <= 10 & method=="IV" & fstat< 30 , title("F less than 30") saving(temp1, replace) width(0.1) start(0) fcolor(gs10) lcolor(gs10) kdensity kdenopts(width(0.1)) ytitle(Density, size(large)) xtitle(z-statistic, size(large)) xline(1.65 1.96 2.58, lwidth(thin)) xlabel(0 1 1.65 "" 1.96 "" 2.58 "" 3 4 5 6 7 8 9 10, labels labsize(large)) ylabel(, labels labsize(large)) legend(off) scheme(s1mono) . histogram t if t <= 10 & method=="IV" & fstat< 30 , title( > "F less than 30") saving("temp1", replace) width(0.1) start( > 0) fcolor(gs10) lcolor(gs10) kdensity kdenopts(width(0.1)) ytitle(Density, si > ze(large)) xtitle(z-statistic, size(large)) xline(1.65 1.96 2.58, lwidth(thin > )) xlabel(0 1 1.65 "" 1.96 "" 2.58 "*" 3 4 5 6 7 8 9 10, labels labsize( > large)) ylabel(, labels labsize(large)) legend(off) scheme(s1mono) (bin=90, start=0, width=.1) file temp1.gph saved .
▼	95	`graph export figure_A1b.pdf, replace` `graph export figure_A1b.pdf, replace . graph export "figure_A1b.pdf", replace file figure_A1b.pdf saved as PDF format .`
	96
▼	97	`histogram t if t <= 10 & method=="IV" & fstat>= 30 , title("F greater than or equal to 30") saving(temp2, replace) width(0.1) start(0) fcolor(gs10) lcolor(gs10) kdensity kdenopts(width(0.1)) ytitle(Density, size(large)) xtitle(z-statistic, size(large)) xline(1.65 1.96 2.58, lwidth(thin)) xlabel(0 1 1.65 "" 1.96 "" 2.58 "*" 3 4 5 6 7 8 9 10, labels labsize(large)) ylabel(, labels labsize(large)) legend(off) scheme(s1mono)` histogram t if t <= 10 & method=="IV" & fstat>= 30 , title("F greater than or equal to 30") saving(temp2, replace) width(0.1) start(0) fcolor(gs10) lcolor(gs10) kdensity kdenopts(width(0.1)) ytitle(Density, size(large)) xtitle(z-statistic, size(large)) xline(1.65 1.96 2.58, lwidth(thin)) xlabel(0 1 1.65 "" 1.96 "" 2.58 "" 3 4 5 6 7 8 9 10, labels labsize(large)) ylabel(, labels labsize(large)) legend(off) scheme(s1mono) . histogram t if t <= 10 & method=="IV" & fstat>= 30 , title > ("F greater than or equal to 30") saving("temp2", replace) w > idth(0.1) start(0) fcolor(gs10) lcolor(gs10) kdensity kdenopts(width(0.1)) yt > itle(Density, size(large)) xtitle(z-statistic, size(large)) xline(1.65 1.96 2 > .58, lwidth(thin)) xlabel(0 1 1.65 "" 1.96 "" 2.58 "*" 3 4 5 6 7 8 9 10, > labels labsize(large)) ylabel(, labels labsize(large)) legend(off) scheme(s1 > mono) (bin=100, start=0, width=.1) file temp2.gph saved .
▼	98	`graph export figure_A1c.pdf, replace` `graph export figure_A1c.pdf, replace . graph export "figure_A1c.pdf", replace file figure_A1c.pdf saved as PDF format .`
	99
	100
	101	`*** Figure A2 in our comment`
	102
	103	`* read in the data`
▼	104	`cd "$dir_data"` `cd "/home/rstudio/repbox/projects_ejd/aer_112_9_9/mod/Scripts/Data" . cd "${repbox_path}/Data" /home/rstudio/repbox/projects_ejd/aer_112_9_9/mod/Data .`
▼	105	`capture use "MM Data with WP ready.dta", clear` `. capture use "MM Data with WP ready.dta", clear .`
	106
	107	`* determine folder to store results`
▼	108	`cd "$dir_results"` `cd "/home/rstudio/repbox/projects_ejd/aer_112_9_9/mod/Scripts/Results" . cd "${repbox_path}/Results" /home/rstudio/repbox/projects_ejd/aer_112_9_9/mod/Results .`
	109
	110	`* drop obs with small significand`
▼	111	`keep if keep_obs==1` `. keep if keep_obs==1 (5,626 observations deleted) .`
	112
▼	113	`histogram t if t <= 10 & WP==0, title("Published") saving(temp1, replace) width(0.1) start(0) fcolor(gs10) lcolor(gs10) kdensity kdenopts(width(0.1)) ytitle(Density, size(large)) xtitle(z-statistic, size(large)) xline(1.65 1.96 2.58, lwidth(thin)) xlabel(0 1 1.65 "" 1.96 "" 2.58 "*" 3 4 5 6 7 8 9 10, labels labsize(large)) ylabel(, labels labsize(large)) legend(off) scheme(s1mono)` histogram t if t <= 10 & WP==0, title("Published") saving(temp1, replace) width(0.1) start(0) fcolor(gs10) lcolor(gs10) kdensity kdenopts(width(0.1)) ytitle(Density, size(large)) xtitle(z-statistic, size(large)) xline(1.65 1.96 2.58, lwidth(thin)) xlabel(0 1 1.65 "" 1.96 "" 2.58 "" 3 4 5 6 7 8 9 10, labels labsize(large)) ylabel(, labels labsize(large)) legend(off) scheme(s1mono) . histogram t if t <= 10 & WP==0, title("Published") saving( > "temp1", replace) width(0.1) start(0) fcolor(gs10) lcolor(gs > 10) kdensity kdenopts(width(0.1)) ytitle(Density, size(large)) xtitle(z-stati > stic, size(large)) xline(1.65 1.96 2.58, lwidth(thin)) xlabel(0 1 1.65 "" 1. > 96 "" 2.58 "*" 3 4 5 6 7 8 9 10, labels labsize(large)) ylabel(, labels l > absize(large)) legend(off) scheme(s1mono) (bin=100, start=0, width=.1) file temp1.gph saved .
▼	114	`graph export figure_A2a.pdf, replace` `graph export figure_A2a.pdf, replace . graph export "figure_A2a.pdf", replace file figure_A2a.pdf saved as PDF format .`
▼	115	`histogram t if t <= 10 & WP==1, title("Working Paper") saving(temp2, replace) width(0.1) start(0) fcolor(gs10) lcolor(gs10) kdensity kdenopts(width(0.1)) ytitle(Density, size(large)) xtitle(z-statistic, size(large)) xline(1.65 1.96 2.58, lwidth(thin)) xlabel(0 1 1.65 "" 1.96 "" 2.58 "*" 3 4 5 6 7 8 9 10, labels labsize(large)) ylabel(, labels labsize(large)) legend(off) scheme(s1mono)` histogram t if t <= 10 & WP==1, title("Working Paper") saving(temp2, replace) width(0.1) start(0) fcolor(gs10) lcolor(gs10) kdensity kdenopts(width(0.1)) ytitle(Density, size(large)) xtitle(z-statistic, size(large)) xline(1.65 1.96 2.58, lwidth(thin)) xlabel(0 1 1.65 "" 1.96 "" 2.58 "" 3 4 5 6 7 8 9 10, labels labsize(large)) ylabel(, labels labsize(large)) legend(off) scheme(s1mono) . histogram t if t <= 10 & WP==1, title("Working Paper") sav > ing("temp2", replace) width(0.1) start(0) fcolor(gs10) lcolo > r(gs10) kdensity kdenopts(width(0.1)) ytitle(Density, size(large)) xtitle(z-s > tatistic, size(large)) xline(1.65 1.96 2.58, lwidth(thin)) xlabel(0 1 1.65 " > " 1.96 "" 2.58 "*" 3 4 5 6 7 8 9 10, labels labsize(large)) ylabel(, labe > ls labsize(large)) legend(off) scheme(s1mono) (bin=99, start=0, width=.1) file temp2.gph saved .
▼	116	`graph export figure_A2b.pdf, replace` `graph export figure_A2b.pdf, replace . graph export "figure_A2b.pdf", replace file figure_A2b.pdf saved as PDF format .`
	117

	1	`* this sctipt is borrowed from Brodeur et al. (2020) and executes some variable manipulation, labels variables and drops variables not needed any more`
	2
▼	3	`clear all` `. clear all .`
▼	4	`set more off` `. set more off .`
	5
	6	`* specify directories where data are located and where results should be stored`
▼	7	`global dir_main : pwd` `. global dir_main : pwd .`
▼	8	`global dir_data "$dir_main/Data"` `global dir_data "/home/rstudio/repbox/projects_ejd/aer_112_9_9/mod/Scripts/Data" . global dir_data "$dir_main/Data" .`
▼	9	`global dir_results "$dir_main/Results"` `global dir_results "/home/rstudio/repbox/projects_ejd/aer_112_9_9/mod/Scripts/Results" . global dir_results "$dir_main/Results" .`
	10
	11
▼	12	`cd "$dir_data"` `cd "/home/rstudio/repbox/projects_ejd/aer_112_9_9/mod/Scripts/Data" . cd "${repbox_path}/Data" /home/rstudio/repbox/projects_ejd/aer_112_9_9/mod/Data .`
	13	`* read in the data`
▼	14	`use "MM Data.dta" , clear` `. use "MM Data.dta" , clear .`
	15
	16	`* journals`
▼	17	`rename journal journal_name` `. rename journal journal_name .`
▼	18	`gen journal=.` `. gen journal=. (21,740 missing values generated) .`
▼	19	`replace journal=1 if journal_name=="Quarterly Journal of Economics"` `replace journal=1 if journal_name=="Quarterly Journal of Economics" . replace journal=1 if journal_name=="Quarterly Journal of E > conomics" (840 real changes made) .`
▼	20	`replace journal=3 if journal_name=="Journal of Political Economy"` `replace journal=3 if journal_name=="Journal of Political Economy" . replace journal=3 if journal_name=="Journal of Political E > conomy" (761 real changes made) .`
▼	21	`replace journal=4 if journal_name=="Econometrica"` `. replace journal=4 if journal_name=="Econometrica" (307 real changes made) .`
▼	22	`replace journal=5 if journal_name=="Journal of Finance" // old one, has no effect` `. replace journal=5 if journal_name=="Journal of Finance" (1,135 real changes made) .`
▼	23	`replace journal=5 if journal_name=="Journal of Finance"` `. replace journal=5 if journal_name=="Journal of Finance" (0 real changes made) .`
▼	24	`replace journal=6 if journal_name=="Review of Economic Studies" // old one, has no effect` `replace journal=6 if journal_name=="Review of Economic Studies" . replace journal=6 if journal_name=="Review of Economic Stu > dies" (306 real changes made) .`
▼	25	`replace journal=6 if journal_name=="Review of Economic Studies"` `replace journal=6 if journal_name=="Review of Economic Studies" . replace journal=6 if journal_name=="Review of Economic Stu > dies" (0 real changes made) .`
▼	26	`replace journal=7 if journal_name=="AEJ: Macroeconomics" // old` `. replace journal=7 if journal_name=="AEJ: Macroeconomics" (54 real changes made) .`
▼	27	`replace journal=7 if journal_name=="American Economic Journal: Macroeconomics"` `replace journal=7 if journal_name=="American Economic Journal: Macroeconomics" . replace journal=7 if journal_name=="American Economic Jour > nal: Macroeconomics" (0 real changes made) .`
▼	28	`replace journal=8 if journal_name=="Journal of Economic Growth"` `replace journal=8 if journal_name=="Journal of Economic Growth" . replace journal=8 if journal_name=="Journal of Economic Gr > owth" (100 real changes made) .`
▼	29	`replace journal=9 if journal_name=="Review of Economics and Statistics"` `replace journal=9 if journal_name=="Review of Economics and Statistics" . replace journal=9 if journal_name=="Review of Economics an > d Statistics" (1,484 real changes made) .`
▼	30	`replace journal=11 if journal_name=="American Economic Review"` `replace journal=11 if journal_name=="American Economic Review" . replace journal=11 if journal_name=="American Economic Rev > iew" (1,740 real changes made) .`
▼	31	`replace journal=12 if journal_name=="Economic Policy"` `. replace journal=12 if journal_name=="Economic Policy" (80 real changes made) .`
▼	32	`replace journal=15 if journal_name=="AEJ: Applied Economics" // OLD` `replace journal=15 if journal_name=="AEJ: Applied Economics" . replace journal=15 if journal_name=="AEJ: Applied Economic > s" (2,242 real changes made) .`
▼	33	`replace journal=15 if journal_name=="American Economic Journal: Applied Economics"` `replace journal=15 if journal_name=="American Economic Journal: Applied Economics" . replace journal=15 if journal_name=="American Economic Jou > rnal: Applied Economics" (0 real changes made) .`
▼	34	`replace journal=16 if journal_name=="Journal of the European Economic Association"` `replace journal=16 if journal_name=="Journal of the European Economic Association" . replace journal=16 if journal_name=="Journal of the Europe > an Economic Association" (491 real changes made) .`
▼	35	`replace journal=17 if journal_name=="Review of Financial Studies"` `replace journal=17 if journal_name=="Review of Financial Studies" . replace journal=17 if journal_name=="Review of Financial S > tudies" (963 real changes made) .`
▼	36	`replace journal=18 if journal_name=="Journal of International Economics"` `replace journal=18 if journal_name=="Journal of International Economics" . replace journal=18 if journal_name=="Journal of Internatio > nal Economics" (510 real changes made) .`
▼	37	`replace journal=19 if journal_name=="Economic Journal" // OLD` `. replace journal=19 if journal_name=="Economic Journal" (891 real changes made) .`
▼	38	`replace journal=19 if journal_name=="Economic Journal"` `. replace journal=19 if journal_name=="Economic Journal" (0 real changes made) .`
▼	39	`replace journal=20 if journal_name=="Review of Financial Economics" // OLD` `replace journal=20 if journal_name=="Review of Financial Economics" . replace journal=20 if journal_name=="Review of Financial E > conomics" (0 real changes made) .`
▼	40	`replace journal=20 if journal_name=="Journal of Financial Economics"` `replace journal=20 if journal_name=="Journal of Financial Economics" . replace journal=20 if journal_name=="Journal of Financial > Economics" (635 real changes made) .`
▼	41	`replace journal=21 if journal_name=="Experimental Economics"` `replace journal=21 if journal_name=="Experimental Economics" . replace journal=21 if journal_name=="Experimental Economic > s" (79 real changes made) .`
▼	42	`replace journal=22 if journal_name=="Journal of Development Economics"` `replace journal=22 if journal_name=="Journal of Development Economics" . replace journal=22 if journal_name=="Journal of Developmen > t Economics" (2,818 real changes made) .`
▼	43	`replace journal=23 if journal_name=="Journal of Labor Economics"` `replace journal=23 if journal_name=="Journal of Labor Economics" . replace journal=23 if journal_name=="Journal of Labor Econ > omics" (653 real changes made) .`
▼	44	`replace journal=24 if journal_name=="Journal of Financial Intermediation"` `replace journal=24 if journal_name=="Journal of Financial Intermediation" . replace journal=24 if journal_name=="Journal of Financial > Intermediation" (285 real changes made) .`
▼	45	`replace journal=25 if journal_name=="Journal of Applied Econometrics"` `replace journal=25 if journal_name=="Journal of Applied Econometrics" . replace journal=25 if journal_name=="Journal of Applied Ec > onometrics" (86 real changes made) .`
▼	46	`replace journal=26 if journal_name=="Journal of Human Resources"` `replace journal=26 if journal_name=="Journal of Human Resources" . replace journal=26 if journal_name=="Journal of Human Reso > urces" (752 real changes made) .`
▼	47	`replace journal=27 if journal_name=="AEJ: Economic Policy" // OLD` `. replace journal=27 if journal_name=="AEJ: Economic Policy" > (1,263 real changes made) .`
▼	48	`replace journal=27 if journal_name=="American Economic Journal: Economic Policy"` `replace journal=27 if journal_name=="American Economic Journal: Economic Policy" . replace journal=27 if journal_name=="American Economic Jou > rnal: Economic Policy" (0 real changes made) .`
▼	49	`replace journal=31 if journal_name=="Journal of Urban Economics"` `replace journal=31 if journal_name=="Journal of Urban Economics" . replace journal=31 if journal_name=="Journal of Urban Econ > omics" (660 real changes made) .`
▼	50	`replace journal=32 if journal_name=="Journal of Public Economics"` `replace journal=32 if journal_name=="Journal of Public Economics" . replace journal=32 if journal_name=="Journal of Public Eco > nomics" (2,605 real changes made) .`
	51
▼	52	`gen top5=0 if journal!=.` `. gen top5=0 if journal!=. .`
▼	53	`replace top5=1 if journal==1` `. replace top5=1 if journal==1 (840 real changes made) .`
▼	54	`replace top5=1 if journal==3` `. replace top5=1 if journal==3 (761 real changes made) .`
▼	55	`replace top5=1 if journal==4` `. replace top5=1 if journal==4 (307 real changes made) .`
▼	56	`replace top5=1 if journal==6` `. replace top5=1 if journal==6 (306 real changes made) .`
▼	57	`replace top5=1 if journal==11` `. replace top5=1 if journal==11 (1,740 real changes made) .`
	58
▼	59	`gen FINANCE=0 if journal!=.` `. gen FINANCE=0 if journal!=. .`
▼	60	`replace FINANCE=1 if journal==5` `. replace FINANCE=1 if journal==5 (1,135 real changes made) .`
▼	61	`replace FINANCE=1 if journal==17` `. replace FINANCE=1 if journal==17 (963 real changes made) .`
▼	62	`replace FINANCE=1 if journal==20` `. replace FINANCE=1 if journal==20 (635 real changes made) .`
▼	63	`replace FINANCE=1 if journal==24` `. replace FINANCE=1 if journal==24 (285 real changes made) .`
	64
▼	65	`gen MACRO_GROWTH=0 if journal!=.` `. gen MACRO_GROWTH=0 if journal!=. .`
▼	66	`replace MACRO_GROWTH=1 if journal==7` `. replace MACRO_GROWTH=1 if journal==7 (54 real changes made) .`
▼	67	`replace MACRO_GROWTH=1 if journal==8` `. replace MACRO_GROWTH=1 if journal==8 (100 real changes made) .`
	68
▼	69	`gen GEN_INT=0 if journal!=.` `. gen GEN_INT=0 if journal!=. .`
▼	70	`replace GEN_INT=1 if journal==9` `. replace GEN_INT=1 if journal==9 (1,484 real changes made) .`
▼	71	`replace GEN_INT=1 if journal==12` `. replace GEN_INT=1 if journal==12 (80 real changes made) .`
▼	72	`replace GEN_INT=1 if journal==14` `. replace GEN_INT=1 if journal==14 (0 real changes made) .`
▼	73	`replace GEN_INT=1 if journal==15` `. replace GEN_INT=1 if journal==15 (2,242 real changes made) .`
▼	74	`replace GEN_INT=1 if journal==16` `. replace GEN_INT=1 if journal==16 (491 real changes made) .`
▼	75	`replace GEN_INT=1 if journal==19` `. replace GEN_INT=1 if journal==19 (891 real changes made) .`
▼	76	`replace GEN_INT=1 if journal==25` `. replace GEN_INT=1 if journal==25 (86 real changes made) .`
▼	77	`replace GEN_INT=1 if journal==26` `. replace GEN_INT=1 if journal==26 (752 real changes made) .`
	78
▼	79	`gen EXP=0 if journal!=.` `. gen EXP=0 if journal!=. .`
▼	80	`replace EXP=1 if journal==21` `. replace EXP=1 if journal==21 (79 real changes made) .`
	81
▼	82	`gen DEV=0 if journal!=.` `. gen DEV=0 if journal!=. .`
▼	83	`replace DEV=1 if journal==22` `. replace DEV=1 if journal==22 (2,818 real changes made) .`
	84
▼	85	`gen LABOR=0 if journal!=.` `. gen LABOR=0 if journal!=. .`
▼	86	`replace LABOR=1 if journal==23` `. replace LABOR=1 if journal==23 (653 real changes made) .`
	87
▼	88	`gen PUB=0 if journal!=.` `. gen PUB=0 if journal!=. .`
▼	89	`replace PUB=1 if journal==27` `. replace PUB=1 if journal==27 (1,263 real changes made) .`
▼	90	`replace PUB=1 if journal==32` `. replace PUB=1 if journal==32 (2,605 real changes made) .`
	91
▼	92	`gen URB=0 if journal!=.` `. gen URB=0 if journal!=. .`
▼	93	`replace URB=1 if journal==31` `. replace URB=1 if journal==31 (660 real changes made) .`
	94
	95	`* how reported`
▼	96	`gen p_value=1 if report=="p"` `. gen p_value=1 if report=="p" (20,726 missing values generated) .`
▼	97	`gen z_stat=1 if report=="s"` `. gen z_stat=1 if report=="s" (2,009 missing values generated) .`
▼	98	`gen t_stat=1 if report=="t"` `. gen t_stat=1 if report=="t" (20,768 missing values generated) .`
	99
▼	100	`replace p_value=0 if report=="s"` `. replace p_value=0 if report=="s" (19,731 real changes made) .`
▼	101	`replace p_value=0 if report=="t"` `. replace p_value=0 if report=="t" (972 real changes made) .`
▼	102	`replace z_stat=0 if report=="p"` `. replace z_stat=0 if report=="p" (1,014 real changes made) .`
▼	103	`replace z_stat=0 if report=="t"` `. replace z_stat=0 if report=="t" (972 real changes made) .`
▼	104	`replace t_stat=0 if report=="p"` `. replace t_stat=0 if report=="p" (1,014 real changes made) .`
▼	105	`replace t_stat=0 if report=="s"` `. replace t_stat=0 if report=="s" (19,731 real changes made) .`
	106
▼	107	`encode report, gen(ireport)` `. encode report, gen(ireport) .`
	108
	109	`* unique identifiers`
▼	110	`capture egen unique_j = group(journal)` `. capture egen unique_j = group(journal) .`
▼	111	`capture egen unique_ja = group(journal article)` `. capture egen unique_ja = group(journal article) .`
▼	112	`capture egen unique_jat = group(journal article table)` `. capture egen unique_jat = group(journal article table) .`
	113
	114	`* weights`
▼	115	`gen journal_cluster=journal10000` `. gen journal_cluster=journal10000 .`
	116
▼	117	`egen journal_article_cluster=concat(journal_cluster article)` `egen journal_article_cluster=concat(journal_cluster article) . egen journal_article_cluster=concat(journal_cluster articl > e) .`
▼	118	`destring journal_article_cluster, replace` `. destring journal_article_cluster, replace journal_article_cluster: all characters numeric; replaced as long .`
	119
▼	120	`egen journal_article=concat(journal article)` `. egen journal_article=concat(journal article) .`
▼	121	`destring journal_article, replace` `. destring journal_article, replace journal_article: all characters numeric; replaced as int .`
	122
▼	123	`egen article_table=concat(journal_article_cluster table)` `. egen article_table=concat(journal_article_cluster table) .`
▼	124	`destring article_table, replace` `. destring article_table, replace article_table: contains nonnumeric characters; no replace .`
	125
▼	126	`bysort journal_article_cluster: gen test_count = _N` `. bysort journal_article_cluster: gen test_count = _N .`
▼	127	`gen aw_d=1/test_count` `. gen aw_d=1/test_count .`
▼	128	`gen aw=aw_d10000` `. gen aw=aw_d10000 .`
	129
▼	130	`bysort article_table: gen test_count_1 = _N` `. bysort article_table: gen test_count_1 = _N .`
▼	131	`gen aw_tab_d=1/test_count_1` `. gen aw_tab_d=1/test_count_1 .`
▼	132	`gen aw_tab=aw_tab_d10000` `. gen aw_tab=aw_tab_d10000 .`
	133
	134
	135
	136	`* method identifiers`
▼	137	`gen RCT=.` `. gen RCT=. (21,740 missing values generated) .`
▼	138	`replace RCT=1 if method=="RCT"` `. replace RCT=1 if method=="RCT" (7,569 real changes made) .`
▼	139	`replace RCT=0 if method!="RCT"` `. replace RCT=0 if method!="RCT" (14,171 real changes made) .`
	140
▼	141	`gen DID=.` `. gen DID=. (21,740 missing values generated) .`
▼	142	`replace DID=1 if method=="DID"` `. replace DID=1 if method=="DID" (5,853 real changes made) .`
▼	143	`replace DID=0 if method!="DID"` `. replace DID=0 if method!="DID" (15,887 real changes made) .`
	144
▼	145	`gen IV=.` `. gen IV=. (21,740 missing values generated) .`
▼	146	`replace IV=1 if method=="IV"` `. replace IV=1 if method=="IV" (5,170 real changes made) .`
▼	147	`replace IV=0 if method!="IV"` `. replace IV=0 if method!="IV" (16,570 real changes made) .`
	148
▼	149	`gen RDD=.` `. gen RDD=. (21,740 missing values generated) .`
▼	150	`replace RDD=1 if method=="RDD"` `. replace RDD=1 if method=="RDD" (3,148 real changes made) .`
▼	151	`replace RDD=0 if method!="RDD"` `. replace RDD=0 if method!="RDD" (18,592 real changes made) .`
	152
	153	`* statistical threshold identifiers`
▼	154	`gen sign_1pct=.` `. gen sign_1pct=. (21,740 missing values generated) .`
▼	155	`replace sign_1pct=1 if t!=. & t>2.58` `. replace sign_1pct=1 if t!=. & t>2.58 (7,362 real changes made) .`
▼	156	`replace sign_1pct=0 if t!=. & t<=2.58` `. replace sign_1pct=0 if t!=. & t<=2.58 (14,378 real changes made) .`
	157
▼	158	`gen sign_5pct=.` `. gen sign_5pct=. (21,740 missing values generated) .`
▼	159	`replace sign_5pct=1 if t!=. & t>1.96` `. replace sign_5pct=1 if t!=. & t>1.96 (10,559 real changes made) .`
▼	160	`replace sign_5pct=0 if t!=. & t<=1.96` `. replace sign_5pct=0 if t!=. & t<=1.96 (11,181 real changes made) .`
	161
▼	162	`gen sign_10pct=.` `. gen sign_10pct=. (21,740 missing values generated) .`
▼	163	`replace sign_10pct=1 if t!=. & t>1.65` `. replace sign_10pct=1 if t!=. & t>1.65 (12,252 real changes made) .`
▼	164	`replace sign_10pct=0 if t!=. & t<=1.65` `. replace sign_10pct=0 if t!=. & t<=1.65 (9,488 real changes made) .`
	165
	166	`* num authors`
	167
▼	168	`capture drop num_authors` `. capture drop num_authors .`
▼	169	`egen num_authors = rownonmiss(Author), strok` `. egen num_authors = rownonmiss(Author), strok .`
▼	170	`replace num_authors = 11 if title=="Giving kids a head start: The impact and mechanisms of early commitment of financial aid on poor students in rural China"` `replace num_authors = 11 if title=="Giving kids a head start: The impact and mechanisms of early commitment of financial aid on poor students in rural China" . replace num_authors = 11 if title=="Giving kids a head sta > rt: The impact and mechanisms of early commitment of financial aid on poor st > udents in rural China" (34 real changes made) .`
	171
▼	172	`capture drop authored_solo` `. capture drop authored_solo .`
▼	173	`gen authored_solo = 0` `. gen authored_solo = 0 .`
▼	174	`replace authored_solo = 1 if num_authors==1` `. replace authored_solo = 1 if num_authors==1 (4,360 real changes made) .`
	175
	176
	177	`* genders`
	178	`* ssc inst egenmore // may be necessary`
	179
▼	180	`capture drop authors_gender_string` `. capture drop authors_gender_string .`
▼	181	`gen authors_gender_string=""` `. gen authors_gender_string="" (21,740 missing values generated) .`
▼	182	`replace authors_gender_string=Gender1+Gender2+Gender3+Gender4+Gender5+Gender6+Gender7+Gender8+Gender9+Gender10+Gender11` `replace authors_gender_string=Gender1+Gender2+Gender3+Gender4+Gender5+Gender6+Gender7+Gender8+Gender9+Gender10+Gender11 . replace authors_gender_string=Gender1+Gender2+Gender3+Gend > er4+Gender5+Gender6+Gender7+Gender8+Gender9+Gender10+Gender11 variable authors_gender_string was str1 now str11 (21,740 real changes made) .`
	183
▼	184	`capture drop num_male_authors` `. capture drop num_male_authors .`
▼	185	`egen num_male_authors = nss(authors_gender_string) , find(m)` `egen num_male_authors = nss(authors_gender_string) , find(m) . egen num_male_authors = nss(authors_gender_string) , find( > m) .`
	186
▼	187	`capture drop num_female_authors` `. capture drop num_female_authors .`
▼	188	`egen num_female_authors = nss(authors_gender_string) , find(f)` `egen num_female_authors = nss(authors_gender_string) , find(f) . egen num_female_authors = nss(authors_gender_string) , fin > d(f) .`
	189
▼	190	`capture drop share_male_authors` `. capture drop share_male_authors .`
▼	191	`gen share_male_authors = num_male_authors / num_authors` `. gen share_male_authors = num_male_authors / num_authors .`
	192
▼	193	`capture drop share_female_authors` `. capture drop share_female_authors .`
▼	194	`gen share_female_authors = num_female_authors / num_authors` `gen share_female_authors = num_female_authors / num_authors . gen share_female_authors = num_female_authors / num_author > s .`
	195
	196
	197
	198	`* experience`
▼	199	`replace PhDYear1 = "1989" if PhDYear1=="2989"` `. replace PhDYear1 = "1989" if PhDYear1=="2989" (2 real changes made) .`
	200
▼	201	`forval i = 1(1)11 {` `forval i = 1(1)11 {`
▼	202	capture drop PhDYear`i'sieve Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `capture drop PhDYear1sieve` `capture drop PhDYear2sieve` `capture drop PhDYear3sieve` `capture drop PhDYear4sieve` `capture drop PhDYear5sieve` `capture drop PhDYear6sieve` `capture drop PhDYear7sieve` `capture drop PhDYear8sieve` `capture drop PhDYear9sieve` `capture drop PhDYear10sieve` `capture drop PhDYear11sieve`
▼	203	egen PhDYear`i'sieve = sieve(PhDYear`i'), keep(numeric) Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `egen PhDYear1sieve = sieve(PhDYear1), keep(numeric) (536 missing values generated)` `egen PhDYear2sieve = sieve(PhDYear2), keep(numeric) (4,982 missing values generated)` `egen PhDYear3sieve = sieve(PhDYear3), keep(numeric) (10,559 missing values generated)` `egen PhDYear4sieve = sieve(PhDYear4), keep(numeric) (17,980 missing values generated)` `egen PhDYear5sieve = sieve(PhDYear5), keep(numeric) (20,534 missing values generated)` `egen PhDYear6sieve = sieve(PhDYear6), keep(numeric) (21,693 missing values generated)` `egen PhDYear7sieve = sieve(PhDYear7), keep(numeric) (21,740 missing values generated)` `egen PhDYear8sieve = sieve(PhDYear8), keep(numeric) (21,706 missing values generated)` `egen PhDYear9sieve = sieve(PhDYear9), keep(numeric) (21,706 missing values generated)` `egen PhDYear10sieve = sieve(PhDYear10), keep(numeric) (21,740 missing values generated)` `egen PhDYear11sieve = sieve(PhDYear11), keep(numeric) (21,706 missing values generated)`
▼	204	destring PhDYear`i'sieve, replace Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `destring PhDYear1sieve, replace PhDYear1sieve: all characters numeric; replaced as int (536 missing values generated)` `destring PhDYear2sieve, replace PhDYear2sieve: all characters numeric; replaced as int (4982 missing values generated)` `destring PhDYear3sieve, replace PhDYear3sieve: all characters numeric; replaced as int (10559 missing values generated)` `destring PhDYear4sieve, replace PhDYear4sieve: all characters numeric; replaced as int (17980 missing values generated)` `destring PhDYear5sieve, replace PhDYear5sieve: all characters numeric; replaced as int (20534 missing values generated)` `destring PhDYear6sieve, replace PhDYear6sieve: all characters numeric; replaced as int (21693 missing values generated)` `destring PhDYear7sieve, replace PhDYear7sieve: all characters numeric; replaced as byte (21740 missing values generated)` `destring PhDYear8sieve, replace PhDYear8sieve: all characters numeric; replaced as int (21706 missing values generated)` `destring PhDYear9sieve, replace PhDYear9sieve: all characters numeric; replaced as int (21706 missing values generated)` `destring PhDYear10sieve, replace PhDYear10sieve: all characters numeric; replaced as byte (21740 missing values generated)` `destring PhDYear11sieve, replace PhDYear11sieve: all characters numeric; replaced as int (21706 missing values generated)`
▼	205	replace PhDYear`i'sieve = . if PhDYear`i'sieve==0 Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace PhDYear1sieve = . if PhDYear1sieve==0 (0 real changes made)` `replace PhDYear2sieve = . if PhDYear2sieve==0 (0 real changes made)` `replace PhDYear3sieve = . if PhDYear3sieve==0 (0 real changes made)` `replace PhDYear4sieve = . if PhDYear4sieve==0 (0 real changes made)` `replace PhDYear5sieve = . if PhDYear5sieve==0 (12 real changes made, 12 to missing)` `replace PhDYear6sieve = . if PhDYear6sieve==0 (0 real changes made)` `replace PhDYear7sieve = . if PhDYear7sieve==0 (0 real changes made)` `replace PhDYear8sieve = . if PhDYear8sieve==0 (0 real changes made)` `replace PhDYear9sieve = . if PhDYear9sieve==0 (0 real changes made)` `replace PhDYear10sieve = . if PhDYear10sieve==0 (0 real changes made)` `replace PhDYear11sieve = . if PhDYear11sieve==0 (0 real changes made)`
▼	206	replace PhDYear`i'sieve = . if PhDYear`i'sieve==9999 Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace PhDYear1sieve = . if PhDYear1sieve==9999 (0 real changes made)` `replace PhDYear2sieve = . if PhDYear2sieve==9999 (0 real changes made)` `replace PhDYear3sieve = . if PhDYear3sieve==9999 (0 real changes made)` `replace PhDYear4sieve = . if PhDYear4sieve==9999 (0 real changes made)` `replace PhDYear5sieve = . if PhDYear5sieve==9999 (0 real changes made)` `replace PhDYear6sieve = . if PhDYear6sieve==9999 (0 real changes made)` `replace PhDYear7sieve = . if PhDYear7sieve==9999 (0 real changes made)` `replace PhDYear8sieve = . if PhDYear8sieve==9999 (0 real changes made)` `replace PhDYear9sieve = . if PhDYear9sieve==9999 (0 real changes made)` `replace PhDYear10sieve = . if PhDYear10sieve==9999 (0 real changes made)` `replace PhDYear11sieve = . if PhDYear11sieve==9999 (0 real changes made)`
▼	207	capture drop experience`i' Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `capture drop experience1` `capture drop experience2` `capture drop experience3` `capture drop experience4` `capture drop experience5` `capture drop experience6` `capture drop experience7` `capture drop experience8` `capture drop experience9` `capture drop experience10` `capture drop experience11`
▼	208	gen experience`i' = year-PhDYear`i'sieve Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `gen experience1 = year-PhDYear1sieve (536 missing values generated)` `gen experience2 = year-PhDYear2sieve (4,982 missing values generated)` `gen experience3 = year-PhDYear3sieve (10,559 missing values generated)` `gen experience4 = year-PhDYear4sieve (17,980 missing values generated)` `gen experience5 = year-PhDYear5sieve (20,546 missing values generated)` `gen experience6 = year-PhDYear6sieve (21,693 missing values generated)` `gen experience7 = year-PhDYear7sieve (21,740 missing values generated)` `gen experience8 = year-PhDYear8sieve (21,706 missing values generated)` `gen experience9 = year-PhDYear9sieve (21,706 missing values generated)` `gen experience10 = year-PhDYear10sieve (21,740 missing values generated)` `gen experience11 = year-PhDYear11sieve (21,706 missing values generated)`
▼	209	replace experience`i' = . if experience`i'<0 Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace experience1 = . if experience1<0 (157 real changes made, 157 to missing)` `replace experience2 = . if experience2<0 (330 real changes made, 330 to missing)` `replace experience3 = . if experience3<0 (156 real changes made, 156 to missing)` `replace experience4 = . if experience4<0 (102 real changes made, 102 to missing)` `replace experience5 = . if experience5<0 (0 real changes made)` `replace experience6 = . if experience6<0 (0 real changes made)` `replace experience7 = . if experience7<0 (0 real changes made)` `replace experience8 = . if experience8<0 (0 real changes made)` `replace experience9 = . if experience9<0 (0 real changes made)` `replace experience10 = . if experience10<0 (0 real changes made)` `replace experience11 = . if experience11<0 (0 real changes made)`
▼	210	replace experience`i' = . if experience`i' == . Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace experience1 = . if experience1 == . (0 real changes made)` `replace experience2 = . if experience2 == . (0 real changes made)` `replace experience3 = . if experience3 == . (0 real changes made)` `replace experience4 = . if experience4 == . (0 real changes made)` `replace experience5 = . if experience5 == . (0 real changes made)` `replace experience6 = . if experience6 == . (0 real changes made)` `replace experience7 = . if experience7 == . (0 real changes made)` `replace experience8 = . if experience8 == . (0 real changes made)` `replace experience9 = . if experience9 == . (0 real changes made)` `replace experience10 = . if experience10 == . (0 real changes made)` `replace experience11 = . if experience11 == . (0 real changes made)`
	211	`}`
	212
▼	213	`sum PhDYear` . sum PhDYear Variable \| Obs Mean Std. dev. Min Max -------------+--------------------------------------------------------- PhDYear1 \| 0 PhDYear2 \| 0 PhDYear3 \| 0 PhDYear4 \| 0 PhDYear5 \| 0 -------------+--------------------------------------------------------- PhDYear6 \| 0 PhDYear7 \| 0 PhDYear8 \| 0 PhDYear9 \| 0 PhDYear10 \| 0 -------------+--------------------------------------------------------- PhDYear11 \| 0 PhDYear1si~e \| 21,204 2005.547 8.602276 1959 2020 PhDYear2si~e \| 16,758 2005.605 7.854448 1966 2021 PhDYear3si~e \| 11,181 2003.636 9.216486 1972 2020 PhDYear4si~e \| 3,760 2003.947 10.33362 1967 2019 -------------+--------------------------------------------------------- PhDYear5si~e \| 1,194 2002.482 6.53587 1990 2016 PhDYear6si~e \| 47 1987 0 1987 1987 PhDYear7si~e \| 0 PhDYear8si~e \| 34 2002 0 2002 2002 PhDYear9si~e \| 34 2009 0 2009 2009 -------------+--------------------------------------------------------- PhDYear10s~e \| 0 PhDYear11s~e \| 34 1991 0 1991 1991 .
	214
▼	215	`sum experience` . sum experience Variable \| Obs Mean Std. dev. Min Max -------------+--------------------------------------------------------- experience1 \| 21,047 10.99587 8.45535 0 59 experience2 \| 16,428 11.14305 7.52349 0 49 experience3 \| 11,025 13.04599 8.78391 0 43 experience4 \| 3,658 13.0205 9.917178 1 48 experience5 \| 1,194 14.75963 6.739682 2 28 -------------+--------------------------------------------------------- experience6 \| 47 28 0 28 28 experience7 \| 0 experience8 \| 34 13 0 13 13 experience9 \| 34 6 0 6 6 experience10 \| 0 -------------+--------------------------------------------------------- experience11 \| 34 24 0 24 24 .
	216
▼	217	`capture drop experience_avg` `. capture drop experience_avg .`
▼	218	`capture drop experience_avg_sq` `. capture drop experience_avg_sq .`
	219
▼	220	`egen experience_avg = rowmean(experience)` `. egen experience_avg = rowmean(experience) (71 missing values generated) .`
▼	221	`replace experience_avg = 0 if experience_avg==.` `. replace experience_avg = 0 if experience_avg==. (71 real changes made) .`
▼	222	`gen experience_avg_sq = (experience_avg^2)/100` `. gen experience_avg_sq = (experience_avg^2)/100 .`
	223
▼	224	`sum experience` . sum experience Variable \| Obs Mean Std. dev. Min Max -------------+--------------------------------------------------------- experience1 \| 21,047 10.99587 8.45535 0 59 experience2 \| 16,428 11.14305 7.52349 0 49 experience3 \| 11,025 13.04599 8.78391 0 43 experience4 \| 3,658 13.0205 9.917178 1 48 experience5 \| 1,194 14.75963 6.739682 2 28 -------------+--------------------------------------------------------- experience6 \| 47 28 0 28 28 experience7 \| 0 experience8 \| 34 13 0 13 13 experience9 \| 34 6 0 6 6 experience10 \| 0 -------------+--------------------------------------------------------- experience11 \| 34 24 0 24 24 experience~g \| 21,740 10.73031 5.816504 0 38 experience~q \| 21,740 1.489696 1.672511 0 14.44 .
	225
	226
	227	`* editor_present`
	228
▼	229	`forval i = 1(1)11 {` `forval i = 1(1)11 {`
▼	230	destring Editor`i', replace force Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `destring Editor1, replace force Editor1: contains nonnumeric characters; replaced as byte (303 missing values generated)` `destring Editor2, replace force Editor2: contains nonnumeric characters; replaced as byte (4468 missing values generated)` `destring Editor3, replace force Editor3: contains nonnumeric characters; replaced as byte (10451 missing values generated)` `destring Editor4, replace force Editor4: contains nonnumeric characters; replaced as byte (17890 missing values generated)` `destring Editor5, replace force Editor5: contains nonnumeric characters; replaced as byte (20482 missing values generated)` `destring Editor6, replace force Editor6: contains nonnumeric characters; replaced as byte (21437 missing values generated)` `destring Editor7, replace force Editor7: contains nonnumeric characters; replaced as byte (21740 missing values generated)` `destring Editor8, replace force Editor8: all characters numeric; replaced as byte (21706 missing values generated)` `destring Editor9, replace force Editor9: all characters numeric; replaced as byte (21706 missing values generated)` `destring Editor10, replace force Editor10: all characters numeric; replaced as byte (21706 missing values generated)` `destring Editor11, replace force Editor11: all characters numeric; replaced as byte (21706 missing values generated)`
▼	231	replace Editor`i' = 0 if Editor`i'==. Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace Editor1 = 0 if Editor1==. (303 real changes made)` `replace Editor2 = 0 if Editor2==. (4,468 real changes made)` `replace Editor3 = 0 if Editor3==. (10,451 real changes made)` `replace Editor4 = 0 if Editor4==. (17,890 real changes made)` `replace Editor5 = 0 if Editor5==. (20,482 real changes made)` `replace Editor6 = 0 if Editor6==. (21,437 real changes made)` `replace Editor7 = 0 if Editor7==. (21,740 real changes made)` `replace Editor8 = 0 if Editor8==. (21,706 real changes made)` `replace Editor9 = 0 if Editor9==. (21,706 real changes made)` `replace Editor10 = 0 if Editor10==. (21,706 real changes made)` `replace Editor11 = 0 if Editor11==. (21,706 real changes made)`
	232	`}`
	233
▼	234	`capture drop editor_present` `. capture drop editor_present .`
▼	235	`egen editor_present = rowmax(Editor)` `. egen editor_present = rowmax(Editor) .`
	236
	237	`* share_top_authors`
	238
▼	239	`forval i = 1(1)11 {` `forval i = 1(1)11 {`
▼	240	capture drop top_author`i' Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `capture drop top_author1` `capture drop top_author2` `capture drop top_author3` `capture drop top_author4` `capture drop top_author5` `capture drop top_author6` `capture drop top_author7` `capture drop top_author8` `capture drop top_author9` `capture drop top_author10` `capture drop top_author11`
▼	241	gen top_author`i'=0 Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `gen top_author1=0` `gen top_author2=0` `gen top_author3=0` `gen top_author4=0` `gen top_author5=0` `gen top_author6=0` `gen top_author7=0` `gen top_author8=0` `gen top_author9=0` `gen top_author10=0` `gen top_author11=0`
▼	242	replace top_author`i'=. if Author`i'=="" Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_author1=. if Author1=="" (0 real changes made)` `replace top_author2=. if Author2=="" (4,394 real changes made, 4,394 to missing)` `replace top_author3=. if Author3=="" (10,395 real changes made, 10,395 to missing)` `replace top_author4=. if Author4=="" (17,884 real changes made, 17,884 to missing)` `replace top_author5=. if Author5=="" (20,482 real changes made, 20,482 to missing)` `replace top_author6=. if Author6=="" (21,437 real changes made, 21,437 to missing)` `replace top_author7=. if Author7=="" (21,693 real changes made, 21,693 to missing)` `replace top_author8=. if Author8=="" (21,740 real changes made, 21,740 to missing)` `replace top_author9=. if Author9=="" (21,740 real changes made, 21,740 to missing)` `replace top_author10=. if Author10=="" (21,740 real changes made, 21,740 to missing)` `replace top_author11=. if Author11=="" (21,740 real changes made, 21,740 to missing)`
▼	243	replace top_author`i'=1 if strpos(AF`i', "Harvard") Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_author1=1 if strpos(AF1, "Harvard") (1,233 real changes made)` `replace top_author2=1 if strpos(AF2, "Harvard") (747 real changes made)` `replace top_author3=1 if strpos(AF3, "Harvard") (573 real changes made)` `replace top_author4=1 if strpos(AF4, "Harvard") (116 real changes made)` `replace top_author5=1 if strpos(AF5, "Harvard") (22 real changes made)` `replace top_author6=1 if strpos(AF6, "Harvard") (0 real changes made)` `replace top_author7=1 if strpos(AF7, "Harvard") (0 real changes made)` `replace top_author8=1 if strpos(AF8, "Harvard") (0 real changes made)` `replace top_author9=1 if strpos(AF9, "Harvard") (0 real changes made)` `replace top_author10=1 if strpos(AF10, "Harvard") (0 real changes made)` `replace top_author11=1 if strpos(AF11, "Harvard") (0 real changes made)`
▼	244	replace top_author`i'=1 if strpos(AF`i', "Massachusetts Institute of Technology") \| strpos(AF`i', "MIT") Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_author1=1 if strpos(AF1, "Massachusetts Institute of Technology") \| strpos(AF1, "MIT") (1,092 real changes made)` `replace top_author2=1 if strpos(AF2, "Massachusetts Institute of Technology") \| strpos(AF2, "MIT") (226 real changes made)` `replace top_author3=1 if strpos(AF3, "Massachusetts Institute of Technology") \| strpos(AF3, "MIT") (640 real changes made)` `replace top_author4=1 if strpos(AF4, "Massachusetts Institute of Technology") \| strpos(AF4, "MIT") (135 real changes made)` `replace top_author5=1 if strpos(AF5, "Massachusetts Institute of Technology") \| strpos(AF5, "MIT") (0 real changes made)` `replace top_author6=1 if strpos(AF6, "Massachusetts Institute of Technology") \| strpos(AF6, "MIT") (0 real changes made)` `replace top_author7=1 if strpos(AF7, "Massachusetts Institute of Technology") \| strpos(AF7, "MIT") (0 real changes made)` `replace top_author8=1 if strpos(AF8, "Massachusetts Institute of Technology") \| strpos(AF8, "MIT") (0 real changes made)` `replace top_author9=1 if strpos(AF9, "Massachusetts Institute of Technology") \| strpos(AF9, "MIT") (0 real changes made)` `replace top_author10=1 if strpos(AF10, "Massachusetts Institute of Technology") \| strpos(AF10, "MIT") (0 real changes made)` `replace top_author11=1 if strpos(AF11, "Massachusetts Institute of Technology") \| strpos(AF11, "MIT") (0 real changes made)`
▼	245	replace top_author`i'=1 if strpos(AF`i', "Berkeley") Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_author1=1 if strpos(AF1, "Berkeley") (290 real changes made)` `replace top_author2=1 if strpos(AF2, "Berkeley") (683 real changes made)` `replace top_author3=1 if strpos(AF3, "Berkeley") (460 real changes made)` `replace top_author4=1 if strpos(AF4, "Berkeley") (6 real changes made)` `replace top_author5=1 if strpos(AF5, "Berkeley") (0 real changes made)` `replace top_author6=1 if strpos(AF6, "Berkeley") (0 real changes made)` `replace top_author7=1 if strpos(AF7, "Berkeley") (0 real changes made)` `replace top_author8=1 if strpos(AF8, "Berkeley") (0 real changes made)` `replace top_author9=1 if strpos(AF9, "Berkeley") (0 real changes made)` `replace top_author10=1 if strpos(AF10, "Berkeley") (0 real changes made)` `replace top_author11=1 if strpos(AF11, "Berkeley") (0 real changes made)`
▼	246	replace top_author`i'=1 if strpos(AF`i', "University of Chicago") Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_author1=1 if strpos(AF1, "University of Chicago") (594 real changes made)` `replace top_author2=1 if strpos(AF2, "University of Chicago") (395 real changes made)` `replace top_author3=1 if strpos(AF3, "University of Chicago") (724 real changes made)` `replace top_author4=1 if strpos(AF4, "University of Chicago") (69 real changes made)` `replace top_author5=1 if strpos(AF5, "University of Chicago") (0 real changes made)` `replace top_author6=1 if strpos(AF6, "University of Chicago") (0 real changes made)` `replace top_author7=1 if strpos(AF7, "University of Chicago") (0 real changes made)` `replace top_author8=1 if strpos(AF8, "University of Chicago") (0 real changes made)` `replace top_author9=1 if strpos(AF9, "University of Chicago") (0 real changes made)` `replace top_author10=1 if strpos(AF10, "University of Chicago") (0 real changes made)` `replace top_author11=1 if strpos(AF11, "University of Chicago") (0 real changes made)`
▼	247	replace top_author`i'=1 if strpos(AF`i', "Paris School of Economics") \| strpos(AF`i', "PSE") Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_author1=1 if strpos(AF1, "Paris School of Economics") \| strpos(AF1, "PSE") (174 real changes made)` `replace top_author2=1 if strpos(AF2, "Paris School of Economics") \| strpos(AF2, "PSE") (361 real changes made)` `replace top_author3=1 if strpos(AF3, "Paris School of Economics") \| strpos(AF3, "PSE") (189 real changes made)` `replace top_author4=1 if strpos(AF4, "Paris School of Economics") \| strpos(AF4, "PSE") (0 real changes made)` `replace top_author5=1 if strpos(AF5, "Paris School of Economics") \| strpos(AF5, "PSE") (55 real changes made)` `replace top_author6=1 if strpos(AF6, "Paris School of Economics") \| strpos(AF6, "PSE") (0 real changes made)` `replace top_author7=1 if strpos(AF7, "Paris School of Economics") \| strpos(AF7, "PSE") (0 real changes made)` `replace top_author8=1 if strpos(AF8, "Paris School of Economics") \| strpos(AF8, "PSE") (0 real changes made)` `replace top_author9=1 if strpos(AF9, "Paris School of Economics") \| strpos(AF9, "PSE") (0 real changes made)` `replace top_author10=1 if strpos(AF10, "Paris School of Economics") \| strpos(AF10, "PSE") (0 real changes made)` `replace top_author11=1 if strpos(AF11, "Paris School of Economics") \| strpos(AF11, "PSE") (0 real changes made)`
▼	248	replace top_author`i'=1 if strpos(AF`i', "Princeton University") Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_author1=1 if strpos(AF1, "Princeton University") (497 real changes made)` `replace top_author2=1 if strpos(AF2, "Princeton University") (163 real changes made)` `replace top_author3=1 if strpos(AF3, "Princeton University") (18 real changes made)` `replace top_author4=1 if strpos(AF4, "Princeton University") (0 real changes made)` `replace top_author5=1 if strpos(AF5, "Princeton University") (0 real changes made)` `replace top_author6=1 if strpos(AF6, "Princeton University") (0 real changes made)` `replace top_author7=1 if strpos(AF7, "Princeton University") (0 real changes made)` `replace top_author8=1 if strpos(AF8, "Princeton University") (0 real changes made)` `replace top_author9=1 if strpos(AF9, "Princeton University") (0 real changes made)` `replace top_author10=1 if strpos(AF10, "Princeton University") (0 real changes made)` `replace top_author11=1 if strpos(AF11, "Princeton University") (0 real changes made)`
▼	249	replace top_author`i'=1 if strpos(AF`i', "Stanford University") Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_author1=1 if strpos(AF1, "Stanford University") (425 real changes made)` `replace top_author2=1 if strpos(AF2, "Stanford University") (363 real changes made)` `replace top_author3=1 if strpos(AF3, "Stanford University") (18 real changes made)` `replace top_author4=1 if strpos(AF4, "Stanford University") (15 real changes made)` `replace top_author5=1 if strpos(AF5, "Stanford University") (0 real changes made)` `replace top_author6=1 if strpos(AF6, "Stanford University") (0 real changes made)` `replace top_author7=1 if strpos(AF7, "Stanford University") (0 real changes made)` `replace top_author8=1 if strpos(AF8, "Stanford University") (0 real changes made)` `replace top_author9=1 if strpos(AF9, "Stanford University") (34 real changes made)` `replace top_author10=1 if strpos(AF10, "Stanford University") (34 real changes made)` `replace top_author11=1 if strpos(AF11, "Stanford University") (34 real changes made)`
▼	250	replace top_author`i'=1 if strpos(AF`i', "Oxford University") Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_author1=1 if strpos(AF1, "Oxford University") (7 real changes made)` `replace top_author2=1 if strpos(AF2, "Oxford University") (0 real changes made)` `replace top_author3=1 if strpos(AF3, "Oxford University") (12 real changes made)` `replace top_author4=1 if strpos(AF4, "Oxford University") (0 real changes made)` `replace top_author5=1 if strpos(AF5, "Oxford University") (0 real changes made)` `replace top_author6=1 if strpos(AF6, "Oxford University") (0 real changes made)` `replace top_author7=1 if strpos(AF7, "Oxford University") (0 real changes made)` `replace top_author8=1 if strpos(AF8, "Oxford University") (0 real changes made)` `replace top_author9=1 if strpos(AF9, "Oxford University") (0 real changes made)` `replace top_author10=1 if strpos(AF10, "Oxford University") (0 real changes made)` `replace top_author11=1 if strpos(AF11, "Oxford University") (0 real changes made)`
▼	251	replace top_author`i'=1 if strpos(AF`i', "Toulouse School of Economics") \| strpos(AF`i', "TSE") Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_author1=1 if strpos(AF1, "Toulouse School of Economics") \| strpos(AF1, "TSE") (0 real changes made)` `replace top_author2=1 if strpos(AF2, "Toulouse School of Economics") \| strpos(AF2, "TSE") (0 real changes made)` `replace top_author3=1 if strpos(AF3, "Toulouse School of Economics") \| strpos(AF3, "TSE") (0 real changes made)` `replace top_author4=1 if strpos(AF4, "Toulouse School of Economics") \| strpos(AF4, "TSE") (0 real changes made)` `replace top_author5=1 if strpos(AF5, "Toulouse School of Economics") \| strpos(AF5, "TSE") (0 real changes made)` `replace top_author6=1 if strpos(AF6, "Toulouse School of Economics") \| strpos(AF6, "TSE") (0 real changes made)` `replace top_author7=1 if strpos(AF7, "Toulouse School of Economics") \| strpos(AF7, "TSE") (0 real changes made)` `replace top_author8=1 if strpos(AF8, "Toulouse School of Economics") \| strpos(AF8, "TSE") (0 real changes made)` `replace top_author9=1 if strpos(AF9, "Toulouse School of Economics") \| strpos(AF9, "TSE") (0 real changes made)` `replace top_author10=1 if strpos(AF10, "Toulouse School of Economics") \| strpos(AF10, "TSE") (0 real changes made)` `replace top_author11=1 if strpos(AF11, "Toulouse School of Economics") \| strpos(AF11, "TSE") (0 real changes made)`
▼	252	replace top_author`i'=1 if strpos(AF`i', "Columbia University") Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_author1=1 if strpos(AF1, "Columbia University") (220 real changes made)` `replace top_author2=1 if strpos(AF2, "Columbia University") (355 real changes made)` `replace top_author3=1 if strpos(AF3, "Columbia University") (42 real changes made)` `replace top_author4=1 if strpos(AF4, "Columbia University") (0 real changes made)` `replace top_author5=1 if strpos(AF5, "Columbia University") (0 real changes made)` `replace top_author6=1 if strpos(AF6, "Columbia University") (0 real changes made)` `replace top_author7=1 if strpos(AF7, "Columbia University") (0 real changes made)` `replace top_author8=1 if strpos(AF8, "Columbia University") (0 real changes made)` `replace top_author9=1 if strpos(AF9, "Columbia University") (0 real changes made)` `replace top_author10=1 if strpos(AF10, "Columbia University") (0 real changes made)` `replace top_author11=1 if strpos(AF11, "Columbia University") (0 real changes made)`
▼	253	replace top_author`i'=1 if strpos(AF`i', "New York University") \| strpos(AF`i', "NYU") Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_author1=1 if strpos(AF1, "New York University") \| strpos(AF1, "NYU") (137 real changes made)` `replace top_author2=1 if strpos(AF2, "New York University") \| strpos(AF2, "NYU") (258 real changes made)` `replace top_author3=1 if strpos(AF3, "New York University") \| strpos(AF3, "NYU") (163 real changes made)` `replace top_author4=1 if strpos(AF4, "New York University") \| strpos(AF4, "NYU") (103 real changes made)` `replace top_author5=1 if strpos(AF5, "New York University") \| strpos(AF5, "NYU") (0 real changes made)` `replace top_author6=1 if strpos(AF6, "New York University") \| strpos(AF6, "NYU") (0 real changes made)` `replace top_author7=1 if strpos(AF7, "New York University") \| strpos(AF7, "NYU") (0 real changes made)` `replace top_author8=1 if strpos(AF8, "New York University") \| strpos(AF8, "NYU") (0 real changes made)` `replace top_author9=1 if strpos(AF9, "New York University") \| strpos(AF9, "NYU") (0 real changes made)` `replace top_author10=1 if strpos(AF10, "New York University") \| strpos(AF10, "NYU") (0 real changes made)` `replace top_author11=1 if strpos(AF11, "New York University") \| strpos(AF11, "NYU") (0 real changes made)`
▼	254	replace top_author`i'=1 if strpos(AF`i', "Yale University") Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_author1=1 if strpos(AF1, "Yale University") (71 real changes made)` `replace top_author2=1 if strpos(AF2, "Yale University") (227 real changes made)` `replace top_author3=1 if strpos(AF3, "Yale University") (32 real changes made)` `replace top_author4=1 if strpos(AF4, "Yale University") (68 real changes made)` `replace top_author5=1 if strpos(AF5, "Yale University") (0 real changes made)` `replace top_author6=1 if strpos(AF6, "Yale University") (256 real changes made)` `replace top_author7=1 if strpos(AF7, "Yale University") (0 real changes made)` `replace top_author8=1 if strpos(AF8, "Yale University") (0 real changes made)` `replace top_author9=1 if strpos(AF9, "Yale University") (0 real changes made)` `replace top_author10=1 if strpos(AF10, "Yale University") (0 real changes made)` `replace top_author11=1 if strpos(AF11, "Yale University") (0 real changes made)`
▼	255	replace top_author`i'=1 if strpos(AF`i', "Boston University") Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_author1=1 if strpos(AF1, "Boston University") (37 real changes made)` `replace top_author2=1 if strpos(AF2, "Boston University") (67 real changes made)` `replace top_author3=1 if strpos(AF3, "Boston University") (4 real changes made)` `replace top_author4=1 if strpos(AF4, "Boston University") (0 real changes made)` `replace top_author5=1 if strpos(AF5, "Boston University") (0 real changes made)` `replace top_author6=1 if strpos(AF6, "Boston University") (0 real changes made)` `replace top_author7=1 if strpos(AF7, "Boston University") (0 real changes made)` `replace top_author8=1 if strpos(AF8, "Boston University") (0 real changes made)` `replace top_author9=1 if strpos(AF9, "Boston University") (0 real changes made)` `replace top_author10=1 if strpos(AF10, "Boston University") (0 real changes made)` `replace top_author11=1 if strpos(AF11, "Boston University") (0 real changes made)`
▼	256	replace top_author`i'=1 if strpos(AF`i', "Barcelona Graduate School of Economics") \| strpos(AF`i', "Barcelona GSE") Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_author1=1 if strpos(AF1, "Barcelona Graduate School of Economics") \| strpos(AF1, "Barcelona GSE") (92 real changes made)` `replace top_author2=1 if strpos(AF2, "Barcelona Graduate School of Economics") \| strpos(AF2, "Barcelona GSE") (84 real changes made)` `replace top_author3=1 if strpos(AF3, "Barcelona Graduate School of Economics") \| strpos(AF3, "Barcelona GSE") (20 real changes made)` `replace top_author4=1 if strpos(AF4, "Barcelona Graduate School of Economics") \| strpos(AF4, "Barcelona GSE") (0 real changes made)` `replace top_author5=1 if strpos(AF5, "Barcelona Graduate School of Economics") \| strpos(AF5, "Barcelona GSE") (0 real changes made)` `replace top_author6=1 if strpos(AF6, "Barcelona Graduate School of Economics") \| strpos(AF6, "Barcelona GSE") (0 real changes made)` `replace top_author7=1 if strpos(AF7, "Barcelona Graduate School of Economics") \| strpos(AF7, "Barcelona GSE") (0 real changes made)` `replace top_author8=1 if strpos(AF8, "Barcelona Graduate School of Economics") \| strpos(AF8, "Barcelona GSE") (0 real changes made)` `replace top_author9=1 if strpos(AF9, "Barcelona Graduate School of Economics") \| strpos(AF9, "Barcelona GSE") (0 real changes made)` `replace top_author10=1 if strpos(AF10, "Barcelona Graduate School of Economics") \| strpos(AF10, "Barcelona GSE") (0 real changes made)` `replace top_author11=1 if strpos(AF11, "Barcelona Graduate School of Economics") \| strpos(AF11, "Barcelona GSE") (0 real changes made)`
▼	257	replace top_author`i'=1 if strpos(AF`i', "University of California-San Diego") \| strpos(AF`i', "UCSD") Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_author1=1 if strpos(AF1, "University of California-San Diego") \| strpos(AF1, "UCSD") (0 real changes made)` `replace top_author2=1 if strpos(AF2, "University of California-San Diego") \| strpos(AF2, "UCSD") (0 real changes made)` `replace top_author3=1 if strpos(AF3, "University of California-San Diego") \| strpos(AF3, "UCSD") (0 real changes made)` `replace top_author4=1 if strpos(AF4, "University of California-San Diego") \| strpos(AF4, "UCSD") (0 real changes made)` `replace top_author5=1 if strpos(AF5, "University of California-San Diego") \| strpos(AF5, "UCSD") (0 real changes made)` `replace top_author6=1 if strpos(AF6, "University of California-San Diego") \| strpos(AF6, "UCSD") (0 real changes made)` `replace top_author7=1 if strpos(AF7, "University of California-San Diego") \| strpos(AF7, "UCSD") (0 real changes made)` `replace top_author8=1 if strpos(AF8, "University of California-San Diego") \| strpos(AF8, "UCSD") (0 real changes made)` `replace top_author9=1 if strpos(AF9, "University of California-San Diego") \| strpos(AF9, "UCSD") (0 real changes made)` `replace top_author10=1 if strpos(AF10, "University of California-San Diego") \| strpos(AF10, "UCSD") (0 real changes made)` `replace top_author11=1 if strpos(AF11, "University of California-San Diego") \| strpos(AF11, "UCSD") (0 real changes made)`
▼	258	replace top_author`i'=1 if strpos(AF`i', "Dartmouth College") Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_author1=1 if strpos(AF1, "Dartmouth College") (60 real changes made)` `replace top_author2=1 if strpos(AF2, "Dartmouth College") (65 real changes made)` `replace top_author3=1 if strpos(AF3, "Dartmouth College") (89 real changes made)` `replace top_author4=1 if strpos(AF4, "Dartmouth College") (55 real changes made)` `replace top_author5=1 if strpos(AF5, "Dartmouth College") (0 real changes made)` `replace top_author6=1 if strpos(AF6, "Dartmouth College") (0 real changes made)` `replace top_author7=1 if strpos(AF7, "Dartmouth College") (0 real changes made)` `replace top_author8=1 if strpos(AF8, "Dartmouth College") (0 real changes made)` `replace top_author9=1 if strpos(AF9, "Dartmouth College") (0 real changes made)` `replace top_author10=1 if strpos(AF10, "Dartmouth College") (0 real changes made)` `replace top_author11=1 if strpos(AF11, "Dartmouth College") (0 real changes made)`
▼	259	replace top_author`i'=1 if strpos(AF`i', "University of Pennsylvania") Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_author1=1 if strpos(AF1, "University of Pennsylvania") (237 real changes made)` `replace top_author2=1 if strpos(AF2, "University of Pennsylvania") (229 real changes made)` `replace top_author3=1 if strpos(AF3, "University of Pennsylvania") (280 real changes made)` `replace top_author4=1 if strpos(AF4, "University of Pennsylvania") (135 real changes made)` `replace top_author5=1 if strpos(AF5, "University of Pennsylvania") (296 real changes made)` `replace top_author6=1 if strpos(AF6, "University of Pennsylvania") (0 real changes made)` `replace top_author7=1 if strpos(AF7, "University of Pennsylvania") (0 real changes made)` `replace top_author8=1 if strpos(AF8, "University of Pennsylvania") (0 real changes made)` `replace top_author9=1 if strpos(AF9, "University of Pennsylvania") (0 real changes made)` `replace top_author10=1 if strpos(AF10, "University of Pennsylvania") (0 real changes made)` `replace top_author11=1 if strpos(AF11, "University of Pennsylvania") (0 real changes made)`
▼	260	replace top_author`i'=1 if strpos(AF`i', "University College London") \| strpos(AF`i', "UCL") Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_author1=1 if strpos(AF1, "University College London") \| strpos(AF1, "UCL") (304 real changes made)` `replace top_author2=1 if strpos(AF2, "University College London") \| strpos(AF2, "UCL") (18 real changes made)` `replace top_author3=1 if strpos(AF3, "University College London") \| strpos(AF3, "UCL") (52 real changes made)` `replace top_author4=1 if strpos(AF4, "University College London") \| strpos(AF4, "UCL") (12 real changes made)` `replace top_author5=1 if strpos(AF5, "University College London") \| strpos(AF5, "UCL") (12 real changes made)` `replace top_author6=1 if strpos(AF6, "University College London") \| strpos(AF6, "UCL") (0 real changes made)` `replace top_author7=1 if strpos(AF7, "University College London") \| strpos(AF7, "UCL") (0 real changes made)` `replace top_author8=1 if strpos(AF8, "University College London") \| strpos(AF8, "UCL") (0 real changes made)` `replace top_author9=1 if strpos(AF9, "University College London") \| strpos(AF9, "UCL") (0 real changes made)` `replace top_author10=1 if strpos(AF10, "University College London") \| strpos(AF10, "UCL") (0 real changes made)` `replace top_author11=1 if strpos(AF11, "University College London") \| strpos(AF11, "UCL") (0 real changes made)`
▼	261	replace top_author`i'=1 if strpos(AF`i', "Northwestern University") Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_author1=1 if strpos(AF1, "Northwestern University") (327 real changes made)` `replace top_author2=1 if strpos(AF2, "Northwestern University") (463 real changes made)` `replace top_author3=1 if strpos(AF3, "Northwestern University") (93 real changes made)` `replace top_author4=1 if strpos(AF4, "Northwestern University") (129 real changes made)` `replace top_author5=1 if strpos(AF5, "Northwestern University") (0 real changes made)` `replace top_author6=1 if strpos(AF6, "Northwestern University") (0 real changes made)` `replace top_author7=1 if strpos(AF7, "Northwestern University") (0 real changes made)` `replace top_author8=1 if strpos(AF8, "Northwestern University") (0 real changes made)` `replace top_author9=1 if strpos(AF9, "Northwestern University") (0 real changes made)` `replace top_author10=1 if strpos(AF10, "Northwestern University") (0 real changes made)` `replace top_author11=1 if strpos(AF11, "Northwestern University") (0 real changes made)`
▼	262	replace top_author`i'=1 if strpos(AF`i', "Columbia University") Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_author1=1 if strpos(AF1, "Columbia University") (0 real changes made)` `replace top_author2=1 if strpos(AF2, "Columbia University") (0 real changes made)` `replace top_author3=1 if strpos(AF3, "Columbia University") (0 real changes made)` `replace top_author4=1 if strpos(AF4, "Columbia University") (0 real changes made)` `replace top_author5=1 if strpos(AF5, "Columbia University") (0 real changes made)` `replace top_author6=1 if strpos(AF6, "Columbia University") (0 real changes made)` `replace top_author7=1 if strpos(AF7, "Columbia University") (0 real changes made)` `replace top_author8=1 if strpos(AF8, "Columbia University") (0 real changes made)` `replace top_author9=1 if strpos(AF9, "Columbia University") (0 real changes made)` `replace top_author10=1 if strpos(AF10, "Columbia University") (0 real changes made)` `replace top_author11=1 if strpos(AF11, "Columbia University") (0 real changes made)`
▼	263	replace top_author`i'=1 if strpos(AF`i', "University of California-Los Angeles ") \| strpos(AF`i', "UCLA") Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_author1=1 if strpos(AF1, "University of California-Los Angeles ") \| strpos(AF1, "UCLA") (0 real changes made)` `replace top_author2=1 if strpos(AF2, "University of California-Los Angeles ") \| strpos(AF2, "UCLA") (0 real changes made)` `replace top_author3=1 if strpos(AF3, "University of California-Los Angeles ") \| strpos(AF3, "UCLA") (0 real changes made)` `replace top_author4=1 if strpos(AF4, "University of California-Los Angeles ") \| strpos(AF4, "UCLA") (0 real changes made)` `replace top_author5=1 if strpos(AF5, "University of California-Los Angeles ") \| strpos(AF5, "UCLA") (0 real changes made)` `replace top_author6=1 if strpos(AF6, "University of California-Los Angeles ") \| strpos(AF6, "UCLA") (0 real changes made)` `replace top_author7=1 if strpos(AF7, "University of California-Los Angeles ") \| strpos(AF7, "UCLA") (0 real changes made)` `replace top_author8=1 if strpos(AF8, "University of California-Los Angeles ") \| strpos(AF8, "UCLA") (0 real changes made)` `replace top_author9=1 if strpos(AF9, "University of California-Los Angeles ") \| strpos(AF9, "UCLA") (0 real changes made)` `replace top_author10=1 if strpos(AF10, "University of California-Los Angeles ") \| strpos(AF10, "UCLA") (0 real changes made)` `replace top_author11=1 if strpos(AF11, "University of California-Los Angeles ") \| strpos(AF11, "UCLA") (0 real changes made)`
▼	264	replace top_author`i'=1 if strpos(AF`i', "London School of Economics") \| strpos(AF`i', "LSE") Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_author1=1 if strpos(AF1, "London School of Economics") \| strpos(AF1, "LSE") (528 real changes made)` `replace top_author2=1 if strpos(AF2, "London School of Economics") \| strpos(AF2, "LSE") (267 real changes made)` `replace top_author3=1 if strpos(AF3, "London School of Economics") \| strpos(AF3, "LSE") (167 real changes made)` `replace top_author4=1 if strpos(AF4, "London School of Economics") \| strpos(AF4, "LSE") (120 real changes made)` `replace top_author5=1 if strpos(AF5, "London School of Economics") \| strpos(AF5, "LSE") (0 real changes made)` `replace top_author6=1 if strpos(AF6, "London School of Economics") \| strpos(AF6, "LSE") (0 real changes made)` `replace top_author7=1 if strpos(AF7, "London School of Economics") \| strpos(AF7, "LSE") (0 real changes made)` `replace top_author8=1 if strpos(AF8, "London School of Economics") \| strpos(AF8, "LSE") (0 real changes made)` `replace top_author9=1 if strpos(AF9, "London School of Economics") \| strpos(AF9, "LSE") (0 real changes made)` `replace top_author10=1 if strpos(AF10, "London School of Economics") \| strpos(AF10, "LSE") (0 real changes made)` `replace top_author11=1 if strpos(AF11, "London School of Economics") \| strpos(AF11, "LSE") (0 real changes made)`
▼	265	replace top_author`i'=1 if strpos(AF`i', "University of Wisconsin-Madison") Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_author1=1 if strpos(AF1, "University of Wisconsin-Madison") (2 real changes made)` `replace top_author2=1 if strpos(AF2, "University of Wisconsin-Madison") (0 real changes made)` `replace top_author3=1 if strpos(AF3, "University of Wisconsin-Madison") (0 real changes made)` `replace top_author4=1 if strpos(AF4, "University of Wisconsin-Madison") (0 real changes made)` `replace top_author5=1 if strpos(AF5, "University of Wisconsin-Madison") (0 real changes made)` `replace top_author6=1 if strpos(AF6, "University of Wisconsin-Madison") (0 real changes made)` `replace top_author7=1 if strpos(AF7, "University of Wisconsin-Madison") (0 real changes made)` `replace top_author8=1 if strpos(AF8, "University of Wisconsin-Madison") (0 real changes made)` `replace top_author9=1 if strpos(AF9, "University of Wisconsin-Madison") (0 real changes made)` `replace top_author10=1 if strpos(AF10, "University of Wisconsin-Madison") (0 real changes made)` `replace top_author11=1 if strpos(AF11, "University of Wisconsin-Madison") (0 real changes made)`
▼	266	replace top_author`i'=1 if strpos(AF`i', "University of Michigan") Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_author1=1 if strpos(AF1, "University of Michigan") (368 real changes made)` `replace top_author2=1 if strpos(AF2, "University of Michigan") (80 real changes made)` `replace top_author3=1 if strpos(AF3, "University of Michigan") (169 real changes made)` `replace top_author4=1 if strpos(AF4, "University of Michigan") (182 real changes made)` `replace top_author5=1 if strpos(AF5, "University of Michigan") (0 real changes made)` `replace top_author6=1 if strpos(AF6, "University of Michigan") (0 real changes made)` `replace top_author7=1 if strpos(AF7, "University of Michigan") (0 real changes made)` `replace top_author8=1 if strpos(AF8, "University of Michigan") (0 real changes made)` `replace top_author9=1 if strpos(AF9, "University of Michigan") (0 real changes made)` `replace top_author10=1 if strpos(AF10, "University of Michigan") (0 real changes made)` `replace top_author11=1 if strpos(AF11, "University of Michigan") (0 real changes made)`
	267	`}`
	268
▼	269	`capture drop share_top_authors` `. capture drop share_top_authors .`
▼	270	egen share_top_authors = rowmean(top_author`i') egen share_top_authors = rowmean(top_author) . egen share_top_authors = rowmean(top_author`i'*) .
	271
	272	`* share_top_phd`
	273
▼	274	`forval i = 1(1)11 {` `forval i = 1(1)11 {`
▼	275	capture drop top_phd`i' Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `capture drop top_phd1` `capture drop top_phd2` `capture drop top_phd3` `capture drop top_phd4` `capture drop top_phd5` `capture drop top_phd6` `capture drop top_phd7` `capture drop top_phd8` `capture drop top_phd9` `capture drop top_phd10` `capture drop top_phd11`
▼	276	gen top_phd`i'=0 Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `gen top_phd1=0` `gen top_phd2=0` `gen top_phd3=0` `gen top_phd4=0` `gen top_phd5=0` `gen top_phd6=0` `gen top_phd7=0` `gen top_phd8=0` `gen top_phd9=0` `gen top_phd10=0` `gen top_phd11=0`
▼	277	replace top_phd`i'=. if Author`i'=="" Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_phd1=. if Author1=="" (0 real changes made)` `replace top_phd2=. if Author2=="" (4,394 real changes made, 4,394 to missing)` `replace top_phd3=. if Author3=="" (10,395 real changes made, 10,395 to missing)` `replace top_phd4=. if Author4=="" (17,884 real changes made, 17,884 to missing)` `replace top_phd5=. if Author5=="" (20,482 real changes made, 20,482 to missing)` `replace top_phd6=. if Author6=="" (21,437 real changes made, 21,437 to missing)` `replace top_phd7=. if Author7=="" (21,693 real changes made, 21,693 to missing)` `replace top_phd8=. if Author8=="" (21,740 real changes made, 21,740 to missing)` `replace top_phd9=. if Author9=="" (21,740 real changes made, 21,740 to missing)` `replace top_phd10=. if Author10=="" (21,740 real changes made, 21,740 to missing)` `replace top_phd11=. if Author11=="" (21,740 real changes made, 21,740 to missing)`
▼	278	replace top_phd`i'=1 if strpos(PhDInstitution`i', "Harvard") Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_phd1=1 if strpos(PhDInstitution1, "Harvard") (2,389 real changes made)` `replace top_phd2=1 if strpos(PhDInstitution2, "Harvard") (1,758 real changes made)` `replace top_phd3=1 if strpos(PhDInstitution3, "Harvard") (968 real changes made)` `replace top_phd4=1 if strpos(PhDInstitution4, "Harvard") (483 real changes made)` `replace top_phd5=1 if strpos(PhDInstitution5, "Harvard") (43 real changes made)` `replace top_phd6=1 if strpos(PhDInstitution6, "Harvard") (0 real changes made)` `replace top_phd7=1 if strpos(PhDInstitution7, "Harvard") (0 real changes made)` `replace top_phd8=1 if strpos(PhDInstitution8, "Harvard") (0 real changes made)` `replace top_phd9=1 if strpos(PhDInstitution9, "Harvard") (0 real changes made)` `replace top_phd10=1 if strpos(PhDInstitution10, "Harvard") (0 real changes made)` `replace top_phd11=1 if strpos(PhDInstitution11, "Harvard") (0 real changes made)`
▼	279	replace top_phd`i'=1 if strpos(PhDInstitution`i', "Massachusetts Institute of Technology") \| strpos(PhDInstitution`i', "MIT") Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_phd1=1 if strpos(PhDInstitution1, "Massachusetts Institute of Technology") \| strpos(PhDInstitution1, "MIT") (2,279 real changes made)` `replace top_phd2=1 if strpos(PhDInstitution2, "Massachusetts Institute of Technology") \| strpos(PhDInstitution2, "MIT") (1,427 real changes made)` `replace top_phd3=1 if strpos(PhDInstitution3, "Massachusetts Institute of Technology") \| strpos(PhDInstitution3, "MIT") (1,199 real changes made)` `replace top_phd4=1 if strpos(PhDInstitution4, "Massachusetts Institute of Technology") \| strpos(PhDInstitution4, "MIT") (316 real changes made)` `replace top_phd5=1 if strpos(PhDInstitution5, "Massachusetts Institute of Technology") \| strpos(PhDInstitution5, "MIT") (0 real changes made)` `replace top_phd6=1 if strpos(PhDInstitution6, "Massachusetts Institute of Technology") \| strpos(PhDInstitution6, "MIT") (0 real changes made)` `replace top_phd7=1 if strpos(PhDInstitution7, "Massachusetts Institute of Technology") \| strpos(PhDInstitution7, "MIT") (0 real changes made)` `replace top_phd8=1 if strpos(PhDInstitution8, "Massachusetts Institute of Technology") \| strpos(PhDInstitution8, "MIT") (0 real changes made)` `replace top_phd9=1 if strpos(PhDInstitution9, "Massachusetts Institute of Technology") \| strpos(PhDInstitution9, "MIT") (0 real changes made)` `replace top_phd10=1 if strpos(PhDInstitution10, "Massachusetts Institute of Technology") \| strpos(PhDInstitution10, "MIT") (0 real changes made)` `replace top_phd11=1 if strpos(PhDInstitution11, "Massachusetts Institute of Technology") \| strpos(PhDInstitution11, "MIT") (0 real changes made)`
▼	280	replace top_phd`i'=1 if strpos(PhDInstitution`i', "Berkeley") Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_phd1=1 if strpos(PhDInstitution1, "Berkeley") (1,139 real changes made)` `replace top_phd2=1 if strpos(PhDInstitution2, "Berkeley") (896 real changes made)` `replace top_phd3=1 if strpos(PhDInstitution3, "Berkeley") (549 real changes made)` `replace top_phd4=1 if strpos(PhDInstitution4, "Berkeley") (94 real changes made)` `replace top_phd5=1 if strpos(PhDInstitution5, "Berkeley") (292 real changes made)` `replace top_phd6=1 if strpos(PhDInstitution6, "Berkeley") (0 real changes made)` `replace top_phd7=1 if strpos(PhDInstitution7, "Berkeley") (0 real changes made)` `replace top_phd8=1 if strpos(PhDInstitution8, "Berkeley") (0 real changes made)` `replace top_phd9=1 if strpos(PhDInstitution9, "Berkeley") (0 real changes made)` `replace top_phd10=1 if strpos(PhDInstitution10, "Berkeley") (0 real changes made)` `replace top_phd11=1 if strpos(PhDInstitution11, "Berkeley") (0 real changes made)`
▼	281	replace top_phd`i'=1 if strpos(PhDInstitution`i', "University of Chicago") Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_phd1=1 if strpos(PhDInstitution1, "University of Chicago") (560 real changes made)` `replace top_phd2=1 if strpos(PhDInstitution2, "University of Chicago") (306 real changes made)` `replace top_phd3=1 if strpos(PhDInstitution3, "University of Chicago") (71 real changes made)` `replace top_phd4=1 if strpos(PhDInstitution4, "University of Chicago") (0 real changes made)` `replace top_phd5=1 if strpos(PhDInstitution5, "University of Chicago") (0 real changes made)` `replace top_phd6=1 if strpos(PhDInstitution6, "University of Chicago") (0 real changes made)` `replace top_phd7=1 if strpos(PhDInstitution7, "University of Chicago") (0 real changes made)` `replace top_phd8=1 if strpos(PhDInstitution8, "University of Chicago") (0 real changes made)` `replace top_phd9=1 if strpos(PhDInstitution9, "University of Chicago") (0 real changes made)` `replace top_phd10=1 if strpos(PhDInstitution10, "University of Chicago") (0 real changes made)` `replace top_phd11=1 if strpos(PhDInstitution11, "University of Chicago") (0 real changes made)`
▼	282	replace top_phd`i'=1 if strpos(PhDInstitution`i', "Paris School of Economics") \| strpos(PhDInstitution`i', "PSE") Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_phd1=1 if strpos(PhDInstitution1, "Paris School of Economics") \| strpos(PhDInstitution1, "PSE") (376 real changes made)` `replace top_phd2=1 if strpos(PhDInstitution2, "Paris School of Economics") \| strpos(PhDInstitution2, "PSE") (564 real changes made)` `replace top_phd3=1 if strpos(PhDInstitution3, "Paris School of Economics") \| strpos(PhDInstitution3, "PSE") (105 real changes made)` `replace top_phd4=1 if strpos(PhDInstitution4, "Paris School of Economics") \| strpos(PhDInstitution4, "PSE") (52 real changes made)` `replace top_phd5=1 if strpos(PhDInstitution5, "Paris School of Economics") \| strpos(PhDInstitution5, "PSE") (52 real changes made)` `replace top_phd6=1 if strpos(PhDInstitution6, "Paris School of Economics") \| strpos(PhDInstitution6, "PSE") (0 real changes made)` `replace top_phd7=1 if strpos(PhDInstitution7, "Paris School of Economics") \| strpos(PhDInstitution7, "PSE") (0 real changes made)` `replace top_phd8=1 if strpos(PhDInstitution8, "Paris School of Economics") \| strpos(PhDInstitution8, "PSE") (0 real changes made)` `replace top_phd9=1 if strpos(PhDInstitution9, "Paris School of Economics") \| strpos(PhDInstitution9, "PSE") (0 real changes made)` `replace top_phd10=1 if strpos(PhDInstitution10, "Paris School of Economics") \| strpos(PhDInstitution10, "PSE") (0 real changes made)` `replace top_phd11=1 if strpos(PhDInstitution11, "Paris School of Economics") \| strpos(PhDInstitution11, "PSE") (0 real changes made)`
▼	283	replace top_phd`i'=1 if strpos(PhDInstitution`i', "Princeton University") Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_phd1=1 if strpos(PhDInstitution1, "Princeton University") (32 real changes made)` `replace top_phd2=1 if strpos(PhDInstitution2, "Princeton University") (219 real changes made)` `replace top_phd3=1 if strpos(PhDInstitution3, "Princeton University") (227 real changes made)` `replace top_phd4=1 if strpos(PhDInstitution4, "Princeton University") (6 real changes made)` `replace top_phd5=1 if strpos(PhDInstitution5, "Princeton University") (0 real changes made)` `replace top_phd6=1 if strpos(PhDInstitution6, "Princeton University") (0 real changes made)` `replace top_phd7=1 if strpos(PhDInstitution7, "Princeton University") (0 real changes made)` `replace top_phd8=1 if strpos(PhDInstitution8, "Princeton University") (0 real changes made)` `replace top_phd9=1 if strpos(PhDInstitution9, "Princeton University") (0 real changes made)` `replace top_phd10=1 if strpos(PhDInstitution10, "Princeton University") (0 real changes made)` `replace top_phd11=1 if strpos(PhDInstitution11, "Princeton University") (0 real changes made)`
▼	284	replace top_phd`i'=1 if strpos(PhDInstitution`i', "Stanford University") Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_phd1=1 if strpos(PhDInstitution1, "Stanford University") (310 real changes made)` `replace top_phd2=1 if strpos(PhDInstitution2, "Stanford University") (163 real changes made)` `replace top_phd3=1 if strpos(PhDInstitution3, "Stanford University") (127 real changes made)` `replace top_phd4=1 if strpos(PhDInstitution4, "Stanford University") (36 real changes made)` `replace top_phd5=1 if strpos(PhDInstitution5, "Stanford University") (0 real changes made)` `replace top_phd6=1 if strpos(PhDInstitution6, "Stanford University") (0 real changes made)` `replace top_phd7=1 if strpos(PhDInstitution7, "Stanford University") (0 real changes made)` `replace top_phd8=1 if strpos(PhDInstitution8, "Stanford University") (0 real changes made)` `replace top_phd9=1 if strpos(PhDInstitution9, "Stanford University") (0 real changes made)` `replace top_phd10=1 if strpos(PhDInstitution10, "Stanford University") (0 real changes made)` `replace top_phd11=1 if strpos(PhDInstitution11, "Stanford University") (0 real changes made)`
▼	285	replace top_phd`i'=1 if strpos(PhDInstitution`i', "Oxford University") Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_phd1=1 if strpos(PhDInstitution1, "Oxford University") (79 real changes made)` `replace top_phd2=1 if strpos(PhDInstitution2, "Oxford University") (135 real changes made)` `replace top_phd3=1 if strpos(PhDInstitution3, "Oxford University") (0 real changes made)` `replace top_phd4=1 if strpos(PhDInstitution4, "Oxford University") (59 real changes made)` `replace top_phd5=1 if strpos(PhDInstitution5, "Oxford University") (67 real changes made)` `replace top_phd6=1 if strpos(PhDInstitution6, "Oxford University") (0 real changes made)` `replace top_phd7=1 if strpos(PhDInstitution7, "Oxford University") (0 real changes made)` `replace top_phd8=1 if strpos(PhDInstitution8, "Oxford University") (0 real changes made)` `replace top_phd9=1 if strpos(PhDInstitution9, "Oxford University") (0 real changes made)` `replace top_phd10=1 if strpos(PhDInstitution10, "Oxford University") (0 real changes made)` `replace top_phd11=1 if strpos(PhDInstitution11, "Oxford University") (0 real changes made)`
▼	286	replace top_phd`i'=1 if strpos(PhDInstitution`i', "Toulouse School of Economics") \| strpos(PhDInstitution`i', "TSE") Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_phd1=1 if strpos(PhDInstitution1, "Toulouse School of Economics") \| strpos(PhDInstitution1, "TSE") (35 real changes made)` `replace top_phd2=1 if strpos(PhDInstitution2, "Toulouse School of Economics") \| strpos(PhDInstitution2, "TSE") (0 real changes made)` `replace top_phd3=1 if strpos(PhDInstitution3, "Toulouse School of Economics") \| strpos(PhDInstitution3, "TSE") (0 real changes made)` `replace top_phd4=1 if strpos(PhDInstitution4, "Toulouse School of Economics") \| strpos(PhDInstitution4, "TSE") (18 real changes made)` `replace top_phd5=1 if strpos(PhDInstitution5, "Toulouse School of Economics") \| strpos(PhDInstitution5, "TSE") (0 real changes made)` `replace top_phd6=1 if strpos(PhDInstitution6, "Toulouse School of Economics") \| strpos(PhDInstitution6, "TSE") (0 real changes made)` `replace top_phd7=1 if strpos(PhDInstitution7, "Toulouse School of Economics") \| strpos(PhDInstitution7, "TSE") (0 real changes made)` `replace top_phd8=1 if strpos(PhDInstitution8, "Toulouse School of Economics") \| strpos(PhDInstitution8, "TSE") (0 real changes made)` `replace top_phd9=1 if strpos(PhDInstitution9, "Toulouse School of Economics") \| strpos(PhDInstitution9, "TSE") (0 real changes made)` `replace top_phd10=1 if strpos(PhDInstitution10, "Toulouse School of Economics") \| strpos(PhDInstitution10, "TSE") (0 real changes made)` `replace top_phd11=1 if strpos(PhDInstitution11, "Toulouse School of Economics") \| strpos(PhDInstitution11, "TSE") (0 real changes made)`
▼	287	replace top_phd`i'=1 if strpos(PhDInstitution`i', "Columbia University") Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_phd1=1 if strpos(PhDInstitution1, "Columbia University") (163 real changes made)` `replace top_phd2=1 if strpos(PhDInstitution2, "Columbia University") (97 real changes made)` `replace top_phd3=1 if strpos(PhDInstitution3, "Columbia University") (272 real changes made)` `replace top_phd4=1 if strpos(PhDInstitution4, "Columbia University") (113 real changes made)` `replace top_phd5=1 if strpos(PhDInstitution5, "Columbia University") (256 real changes made)` `replace top_phd6=1 if strpos(PhDInstitution6, "Columbia University") (0 real changes made)` `replace top_phd7=1 if strpos(PhDInstitution7, "Columbia University") (0 real changes made)` `replace top_phd8=1 if strpos(PhDInstitution8, "Columbia University") (0 real changes made)` `replace top_phd9=1 if strpos(PhDInstitution9, "Columbia University") (0 real changes made)` `replace top_phd10=1 if strpos(PhDInstitution10, "Columbia University") (0 real changes made)` `replace top_phd11=1 if strpos(PhDInstitution11, "Columbia University") (0 real changes made)`
▼	288	replace top_phd`i'=1 if strpos(PhDInstitution`i', "New York University") \| strpos(PhDInstitution`i', "NYU") Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_phd1=1 if strpos(PhDInstitution1, "New York University") \| strpos(PhDInstitution1, "NYU") (233 real changes made)` `replace top_phd2=1 if strpos(PhDInstitution2, "New York University") \| strpos(PhDInstitution2, "NYU") (50 real changes made)` `replace top_phd3=1 if strpos(PhDInstitution3, "New York University") \| strpos(PhDInstitution3, "NYU") (358 real changes made)` `replace top_phd4=1 if strpos(PhDInstitution4, "New York University") \| strpos(PhDInstitution4, "NYU") (1 real change made)` `replace top_phd5=1 if strpos(PhDInstitution5, "New York University") \| strpos(PhDInstitution5, "NYU") (6 real changes made)` `replace top_phd6=1 if strpos(PhDInstitution6, "New York University") \| strpos(PhDInstitution6, "NYU") (0 real changes made)` `replace top_phd7=1 if strpos(PhDInstitution7, "New York University") \| strpos(PhDInstitution7, "NYU") (0 real changes made)` `replace top_phd8=1 if strpos(PhDInstitution8, "New York University") \| strpos(PhDInstitution8, "NYU") (0 real changes made)` `replace top_phd9=1 if strpos(PhDInstitution9, "New York University") \| strpos(PhDInstitution9, "NYU") (0 real changes made)` `replace top_phd10=1 if strpos(PhDInstitution10, "New York University") \| strpos(PhDInstitution10, "NYU") (0 real changes made)` `replace top_phd11=1 if strpos(PhDInstitution11, "New York University") \| strpos(PhDInstitution11, "NYU") (0 real changes made)`
▼	289	replace top_phd`i'=1 if strpos(PhDInstitution`i', "Yale University") Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_phd1=1 if strpos(PhDInstitution1, "Yale University") (217 real changes made)` `replace top_phd2=1 if strpos(PhDInstitution2, "Yale University") (309 real changes made)` `replace top_phd3=1 if strpos(PhDInstitution3, "Yale University") (58 real changes made)` `replace top_phd4=1 if strpos(PhDInstitution4, "Yale University") (8 real changes made)` `replace top_phd5=1 if strpos(PhDInstitution5, "Yale University") (0 real changes made)` `replace top_phd6=1 if strpos(PhDInstitution6, "Yale University") (0 real changes made)` `replace top_phd7=1 if strpos(PhDInstitution7, "Yale University") (0 real changes made)` `replace top_phd8=1 if strpos(PhDInstitution8, "Yale University") (0 real changes made)` `replace top_phd9=1 if strpos(PhDInstitution9, "Yale University") (0 real changes made)` `replace top_phd10=1 if strpos(PhDInstitution10, "Yale University") (0 real changes made)` `replace top_phd11=1 if strpos(PhDInstitution11, "Yale University") (0 real changes made)`
▼	290	replace top_phd`i'=1 if strpos(PhDInstitution`i', "Boston University") Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_phd1=1 if strpos(PhDInstitution1, "Boston University") (82 real changes made)` `replace top_phd2=1 if strpos(PhDInstitution2, "Boston University") (144 real changes made)` `replace top_phd3=1 if strpos(PhDInstitution3, "Boston University") (67 real changes made)` `replace top_phd4=1 if strpos(PhDInstitution4, "Boston University") (20 real changes made)` `replace top_phd5=1 if strpos(PhDInstitution5, "Boston University") (0 real changes made)` `replace top_phd6=1 if strpos(PhDInstitution6, "Boston University") (0 real changes made)` `replace top_phd7=1 if strpos(PhDInstitution7, "Boston University") (0 real changes made)` `replace top_phd8=1 if strpos(PhDInstitution8, "Boston University") (0 real changes made)` `replace top_phd9=1 if strpos(PhDInstitution9, "Boston University") (0 real changes made)` `replace top_phd10=1 if strpos(PhDInstitution10, "Boston University") (0 real changes made)` `replace top_phd11=1 if strpos(PhDInstitution11, "Boston University") (0 real changes made)`
▼	291	replace top_phd`i'=1 if strpos(PhDInstitution`i', "Barcelona Graduate School of Economics") \| strpos(PhDInstitution`i', "Barcelona GSE") Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_phd1=1 if strpos(PhDInstitution1, "Barcelona Graduate School of Economics") \| strpos(PhDInstitution1, "Barcelona GSE") (0 real changes made)` `replace top_phd2=1 if strpos(PhDInstitution2, "Barcelona Graduate School of Economics") \| strpos(PhDInstitution2, "Barcelona GSE") (0 real changes made)` `replace top_phd3=1 if strpos(PhDInstitution3, "Barcelona Graduate School of Economics") \| strpos(PhDInstitution3, "Barcelona GSE") (0 real changes made)` `replace top_phd4=1 if strpos(PhDInstitution4, "Barcelona Graduate School of Economics") \| strpos(PhDInstitution4, "Barcelona GSE") (0 real changes made)` `replace top_phd5=1 if strpos(PhDInstitution5, "Barcelona Graduate School of Economics") \| strpos(PhDInstitution5, "Barcelona GSE") (0 real changes made)` `replace top_phd6=1 if strpos(PhDInstitution6, "Barcelona Graduate School of Economics") \| strpos(PhDInstitution6, "Barcelona GSE") (0 real changes made)` `replace top_phd7=1 if strpos(PhDInstitution7, "Barcelona Graduate School of Economics") \| strpos(PhDInstitution7, "Barcelona GSE") (0 real changes made)` `replace top_phd8=1 if strpos(PhDInstitution8, "Barcelona Graduate School of Economics") \| strpos(PhDInstitution8, "Barcelona GSE") (0 real changes made)` `replace top_phd9=1 if strpos(PhDInstitution9, "Barcelona Graduate School of Economics") \| strpos(PhDInstitution9, "Barcelona GSE") (0 real changes made)` `replace top_phd10=1 if strpos(PhDInstitution10, "Barcelona Graduate School of Economics") \| strpos(PhDInstitution10, "Barcelona GSE") (0 real changes made)` `replace top_phd11=1 if strpos(PhDInstitution11, "Barcelona Graduate School of Economics") \| strpos(PhDInstitution11, "Barcelona GSE") (0 real changes made)`
▼	292	replace top_phd`i'=1 if strpos(PhDInstitution`i', "University of California-San Diego") \| strpos(PhDInstitution`i', "UCSD") Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_phd1=1 if strpos(PhDInstitution1, "University of California-San Diego") \| strpos(PhDInstitution1, "UCSD") (140 real changes made)` `replace top_phd2=1 if strpos(PhDInstitution2, "University of California-San Diego") \| strpos(PhDInstitution2, "UCSD") (6 real changes made)` `replace top_phd3=1 if strpos(PhDInstitution3, "University of California-San Diego") \| strpos(PhDInstitution3, "UCSD") (51 real changes made)` `replace top_phd4=1 if strpos(PhDInstitution4, "University of California-San Diego") \| strpos(PhDInstitution4, "UCSD") (0 real changes made)` `replace top_phd5=1 if strpos(PhDInstitution5, "University of California-San Diego") \| strpos(PhDInstitution5, "UCSD") (0 real changes made)` `replace top_phd6=1 if strpos(PhDInstitution6, "University of California-San Diego") \| strpos(PhDInstitution6, "UCSD") (0 real changes made)` `replace top_phd7=1 if strpos(PhDInstitution7, "University of California-San Diego") \| strpos(PhDInstitution7, "UCSD") (0 real changes made)` `replace top_phd8=1 if strpos(PhDInstitution8, "University of California-San Diego") \| strpos(PhDInstitution8, "UCSD") (0 real changes made)` `replace top_phd9=1 if strpos(PhDInstitution9, "University of California-San Diego") \| strpos(PhDInstitution9, "UCSD") (0 real changes made)` `replace top_phd10=1 if strpos(PhDInstitution10, "University of California-San Diego") \| strpos(PhDInstitution10, "UCSD") (0 real changes made)` `replace top_phd11=1 if strpos(PhDInstitution11, "University of California-San Diego") \| strpos(PhDInstitution11, "UCSD") (0 real changes made)`
▼	293	replace top_phd`i'=1 if strpos(PhDInstitution`i', "Dartmouth College") Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_phd1=1 if strpos(PhDInstitution1, "Dartmouth College") (0 real changes made)` `replace top_phd2=1 if strpos(PhDInstitution2, "Dartmouth College") (0 real changes made)` `replace top_phd3=1 if strpos(PhDInstitution3, "Dartmouth College") (0 real changes made)` `replace top_phd4=1 if strpos(PhDInstitution4, "Dartmouth College") (0 real changes made)` `replace top_phd5=1 if strpos(PhDInstitution5, "Dartmouth College") (0 real changes made)` `replace top_phd6=1 if strpos(PhDInstitution6, "Dartmouth College") (0 real changes made)` `replace top_phd7=1 if strpos(PhDInstitution7, "Dartmouth College") (0 real changes made)` `replace top_phd8=1 if strpos(PhDInstitution8, "Dartmouth College") (0 real changes made)` `replace top_phd9=1 if strpos(PhDInstitution9, "Dartmouth College") (0 real changes made)` `replace top_phd10=1 if strpos(PhDInstitution10, "Dartmouth College") (0 real changes made)` `replace top_phd11=1 if strpos(PhDInstitution11, "Dartmouth College") (0 real changes made)`
▼	294	replace top_phd`i'=1 if strpos(PhDInstitution`i', "University of Pennsylvania") Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_phd1=1 if strpos(PhDInstitution1, "University of Pennsylvania") (165 real changes made)` `replace top_phd2=1 if strpos(PhDInstitution2, "University of Pennsylvania") (5 real changes made)` `replace top_phd3=1 if strpos(PhDInstitution3, "University of Pennsylvania") (192 real changes made)` `replace top_phd4=1 if strpos(PhDInstitution4, "University of Pennsylvania") (0 real changes made)` `replace top_phd5=1 if strpos(PhDInstitution5, "University of Pennsylvania") (0 real changes made)` `replace top_phd6=1 if strpos(PhDInstitution6, "University of Pennsylvania") (0 real changes made)` `replace top_phd7=1 if strpos(PhDInstitution7, "University of Pennsylvania") (0 real changes made)` `replace top_phd8=1 if strpos(PhDInstitution8, "University of Pennsylvania") (0 real changes made)` `replace top_phd9=1 if strpos(PhDInstitution9, "University of Pennsylvania") (0 real changes made)` `replace top_phd10=1 if strpos(PhDInstitution10, "University of Pennsylvania") (0 real changes made)` `replace top_phd11=1 if strpos(PhDInstitution11, "University of Pennsylvania") (0 real changes made)`
▼	295	replace top_phd`i'=1 if strpos(PhDInstitution`i', "University College London") \| strpos(PhDInstitution`i', "UCL") Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_phd1=1 if strpos(PhDInstitution1, "University College London") \| strpos(PhDInstitution1, "UCL") (293 real changes made)` `replace top_phd2=1 if strpos(PhDInstitution2, "University College London") \| strpos(PhDInstitution2, "UCL") (265 real changes made)` `replace top_phd3=1 if strpos(PhDInstitution3, "University College London") \| strpos(PhDInstitution3, "UCL") (104 real changes made)` `replace top_phd4=1 if strpos(PhDInstitution4, "University College London") \| strpos(PhDInstitution4, "UCL") (77 real changes made)` `replace top_phd5=1 if strpos(PhDInstitution5, "University College London") \| strpos(PhDInstitution5, "UCL") (71 real changes made)` `replace top_phd6=1 if strpos(PhDInstitution6, "University College London") \| strpos(PhDInstitution6, "UCL") (0 real changes made)` `replace top_phd7=1 if strpos(PhDInstitution7, "University College London") \| strpos(PhDInstitution7, "UCL") (0 real changes made)` `replace top_phd8=1 if strpos(PhDInstitution8, "University College London") \| strpos(PhDInstitution8, "UCL") (0 real changes made)` `replace top_phd9=1 if strpos(PhDInstitution9, "University College London") \| strpos(PhDInstitution9, "UCL") (0 real changes made)` `replace top_phd10=1 if strpos(PhDInstitution10, "University College London") \| strpos(PhDInstitution10, "UCL") (0 real changes made)` `replace top_phd11=1 if strpos(PhDInstitution11, "University College London") \| strpos(PhDInstitution11, "UCL") (0 real changes made)`
▼	296	replace top_phd`i'=1 if strpos(PhDInstitution`i', "Northwestern University") Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_phd1=1 if strpos(PhDInstitution1, "Northwestern University") (0 real changes made)` `replace top_phd2=1 if strpos(PhDInstitution2, "Northwestern University") (72 real changes made)` `replace top_phd3=1 if strpos(PhDInstitution3, "Northwestern University") (12 real changes made)` `replace top_phd4=1 if strpos(PhDInstitution4, "Northwestern University") (12 real changes made)` `replace top_phd5=1 if strpos(PhDInstitution5, "Northwestern University") (0 real changes made)` `replace top_phd6=1 if strpos(PhDInstitution6, "Northwestern University") (0 real changes made)` `replace top_phd7=1 if strpos(PhDInstitution7, "Northwestern University") (0 real changes made)` `replace top_phd8=1 if strpos(PhDInstitution8, "Northwestern University") (0 real changes made)` `replace top_phd9=1 if strpos(PhDInstitution9, "Northwestern University") (0 real changes made)` `replace top_phd10=1 if strpos(PhDInstitution10, "Northwestern University") (0 real changes made)` `replace top_phd11=1 if strpos(PhDInstitution11, "Northwestern University") (0 real changes made)`
▼	297	replace top_phd`i'=1 if strpos(PhDInstitution`i', "Columbia University") Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_phd1=1 if strpos(PhDInstitution1, "Columbia University") (0 real changes made)` `replace top_phd2=1 if strpos(PhDInstitution2, "Columbia University") (0 real changes made)` `replace top_phd3=1 if strpos(PhDInstitution3, "Columbia University") (0 real changes made)` `replace top_phd4=1 if strpos(PhDInstitution4, "Columbia University") (0 real changes made)` `replace top_phd5=1 if strpos(PhDInstitution5, "Columbia University") (0 real changes made)` `replace top_phd6=1 if strpos(PhDInstitution6, "Columbia University") (0 real changes made)` `replace top_phd7=1 if strpos(PhDInstitution7, "Columbia University") (0 real changes made)` `replace top_phd8=1 if strpos(PhDInstitution8, "Columbia University") (0 real changes made)` `replace top_phd9=1 if strpos(PhDInstitution9, "Columbia University") (0 real changes made)` `replace top_phd10=1 if strpos(PhDInstitution10, "Columbia University") (0 real changes made)` `replace top_phd11=1 if strpos(PhDInstitution11, "Columbia University") (0 real changes made)`
▼	298	replace top_phd`i'=1 if strpos(PhDInstitution`i', "University of California-Los Angeles ") \| strpos(PhDInstitution`i', "UCLA") Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_phd1=1 if strpos(PhDInstitution1, "University of California-Los Angeles ") \| strpos(PhDInstitution1, "UCLA") (0 real changes made)` `replace top_phd2=1 if strpos(PhDInstitution2, "University of California-Los Angeles ") \| strpos(PhDInstitution2, "UCLA") (0 real changes made)` `replace top_phd3=1 if strpos(PhDInstitution3, "University of California-Los Angeles ") \| strpos(PhDInstitution3, "UCLA") (0 real changes made)` `replace top_phd4=1 if strpos(PhDInstitution4, "University of California-Los Angeles ") \| strpos(PhDInstitution4, "UCLA") (0 real changes made)` `replace top_phd5=1 if strpos(PhDInstitution5, "University of California-Los Angeles ") \| strpos(PhDInstitution5, "UCLA") (0 real changes made)` `replace top_phd6=1 if strpos(PhDInstitution6, "University of California-Los Angeles ") \| strpos(PhDInstitution6, "UCLA") (0 real changes made)` `replace top_phd7=1 if strpos(PhDInstitution7, "University of California-Los Angeles ") \| strpos(PhDInstitution7, "UCLA") (0 real changes made)` `replace top_phd8=1 if strpos(PhDInstitution8, "University of California-Los Angeles ") \| strpos(PhDInstitution8, "UCLA") (0 real changes made)` `replace top_phd9=1 if strpos(PhDInstitution9, "University of California-Los Angeles ") \| strpos(PhDInstitution9, "UCLA") (0 real changes made)` `replace top_phd10=1 if strpos(PhDInstitution10, "University of California-Los Angeles ") \| strpos(PhDInstitution10, "UCLA") (0 real changes made)` `replace top_phd11=1 if strpos(PhDInstitution11, "University of California-Los Angeles ") \| strpos(PhDInstitution11, "UCLA") (0 real changes made)`
▼	299	replace top_phd`i'=1 if strpos(PhDInstitution`i', "London School of Economics") \| strpos(PhDInstitution`i', "LSE") Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_phd1=1 if strpos(PhDInstitution1, "London School of Economics") \| strpos(PhDInstitution1, "LSE") (715 real changes made)` `replace top_phd2=1 if strpos(PhDInstitution2, "London School of Economics") \| strpos(PhDInstitution2, "LSE") (147 real changes made)` `replace top_phd3=1 if strpos(PhDInstitution3, "London School of Economics") \| strpos(PhDInstitution3, "LSE") (289 real changes made)` `replace top_phd4=1 if strpos(PhDInstitution4, "London School of Economics") \| strpos(PhDInstitution4, "LSE") (56 real changes made)` `replace top_phd5=1 if strpos(PhDInstitution5, "London School of Economics") \| strpos(PhDInstitution5, "LSE") (0 real changes made)` `replace top_phd6=1 if strpos(PhDInstitution6, "London School of Economics") \| strpos(PhDInstitution6, "LSE") (0 real changes made)` `replace top_phd7=1 if strpos(PhDInstitution7, "London School of Economics") \| strpos(PhDInstitution7, "LSE") (0 real changes made)` `replace top_phd8=1 if strpos(PhDInstitution8, "London School of Economics") \| strpos(PhDInstitution8, "LSE") (0 real changes made)` `replace top_phd9=1 if strpos(PhDInstitution9, "London School of Economics") \| strpos(PhDInstitution9, "LSE") (0 real changes made)` `replace top_phd10=1 if strpos(PhDInstitution10, "London School of Economics") \| strpos(PhDInstitution10, "LSE") (0 real changes made)` `replace top_phd11=1 if strpos(PhDInstitution11, "London School of Economics") \| strpos(PhDInstitution11, "LSE") (0 real changes made)`
▼	300	replace top_phd`i'=1 if strpos(PhDInstitution`i', "University of Wisconsin-Madison") Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_phd1=1 if strpos(PhDInstitution1, "University of Wisconsin-Madison") (97 real changes made)` `replace top_phd2=1 if strpos(PhDInstitution2, "University of Wisconsin-Madison") (60 real changes made)` `replace top_phd3=1 if strpos(PhDInstitution3, "University of Wisconsin-Madison") (5 real changes made)` `replace top_phd4=1 if strpos(PhDInstitution4, "University of Wisconsin-Madison") (0 real changes made)` `replace top_phd5=1 if strpos(PhDInstitution5, "University of Wisconsin-Madison") (0 real changes made)` `replace top_phd6=1 if strpos(PhDInstitution6, "University of Wisconsin-Madison") (0 real changes made)` `replace top_phd7=1 if strpos(PhDInstitution7, "University of Wisconsin-Madison") (0 real changes made)` `replace top_phd8=1 if strpos(PhDInstitution8, "University of Wisconsin-Madison") (0 real changes made)` `replace top_phd9=1 if strpos(PhDInstitution9, "University of Wisconsin-Madison") (0 real changes made)` `replace top_phd10=1 if strpos(PhDInstitution10, "University of Wisconsin-Madison") (0 real changes made)` `replace top_phd11=1 if strpos(PhDInstitution11, "University of Wisconsin-Madison") (0 real changes made)`
▼	301	replace top_phd`i'=1 if strpos(PhDInstitution`i', "University of Michigan") Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Run 11 `replace top_phd1=1 if strpos(PhDInstitution1, "University of Michigan") (227 real changes made)` `replace top_phd2=1 if strpos(PhDInstitution2, "University of Michigan") (201 real changes made)` `replace top_phd3=1 if strpos(PhDInstitution3, "University of Michigan") (57 real changes made)` `replace top_phd4=1 if strpos(PhDInstitution4, "University of Michigan") (6 real changes made)` `replace top_phd5=1 if strpos(PhDInstitution5, "University of Michigan") (0 real changes made)` `replace top_phd6=1 if strpos(PhDInstitution6, "University of Michigan") (0 real changes made)` `replace top_phd7=1 if strpos(PhDInstitution7, "University of Michigan") (0 real changes made)` `replace top_phd8=1 if strpos(PhDInstitution8, "University of Michigan") (0 real changes made)` `replace top_phd9=1 if strpos(PhDInstitution9, "University of Michigan") (0 real changes made)` `replace top_phd10=1 if strpos(PhDInstitution10, "University of Michigan") (0 real changes made)` `replace top_phd11=1 if strpos(PhDInstitution11, "University of Michigan") (0 real changes made)`
	302	`}`
	303
▼	304	`capture drop share_top_phd` `. capture drop share_top_phd .`
▼	305	egen share_top_phd = rowmean(top_phd`i') egen share_top_phd = rowmean(top_phd) . egen share_top_phd = rowmean(top_phd`i'*) .
	306
▼	307	`capture drop min_table` `. capture drop min_table .`
▼	308	`capture drop main_table` `. capture drop main_table .`
▼	309	`egen min_table = min(table), by(journal_article_cluster)` `. egen min_table = min(table), by(journal_article_cluster) .`
▼	310	`gen main_table = .` `. gen main_table = . (21,740 missing values generated) .`
▼	311	`replace main_table = 1 if min_table == table` `. replace main_table = 1 if min_table == table (7,049 real changes made) .`
	312
▼	313	`gen rct_registered=0 if RCT!=.` `. gen rct_registered=0 if RCT!=. .`
▼	314	`replace rct_registered=1 if rct_pre_registered==1` `. replace rct_registered=1 if rct_pre_registered==1 (280 real changes made) .`
▼	315	`destring registered, replace` `. destring registered, replace registered: all characters numeric; replaced as byte (17574 missing values generated) .`
▼	316	`replace rct_registered=1 if registered==1` `. replace rct_registered=1 if registered==1 (1,012 real changes made) .`
	317
▼	318	`gen DID_graph=DID` `. gen DID_graph=DID .`
▼	319	`replace DID_graph=0 if graph_did==0` `. replace DID_graph=0 if graph_did==0 (914 real changes made) .`
	320
▼	321	`gen ambiguous=0 if sign_5pct!=.` `. gen ambiguous=0 if sign_5pct!=. .`
▼	322	`replace ambiguous=1 if journal_name=="Journal of Urban Economics" & table==7 & article==7 & year==2018` `replace ambiguous=1 if journal_name=="Journal of Urban Economics" & table==7 & article==7 & year==2018 . replace ambiguous=1 if journal_name=="Journal of Urban Eco > nomics" & table==7 & article==7 & year==2018 (8 real changes made) .`
▼	323	`replace ambiguous=1 if Not_sure_shouldbe_included=="1"` `. replace ambiguous=1 if Not_sure_shouldbe_included=="1" (160 real changes made) .`
▼	324	`replace ambiguous=1 if ambig==1` `. replace ambiguous=1 if ambig==1 (128 real changes made) .`
▼	325	`replace ambiguous=1 if abelcomments=="This is an RCT, I would code differently"` `replace ambiguous=1 if abelcomments=="This is an RCT, I would code differently" . replace ambiguous=1 if abelcomments=="This is an RCT, I w > ould code differently" (33 real changes made) .`
▼	326	`replace ambiguous=1 if abelcomments=="not sure which tables to select here"` `replace ambiguous=1 if abelcomments=="not sure which tables to select here" . replace ambiguous=1 if abelcomments=="not sure which table > s to select here" (6 real changes made) .`
▼	327	`replace ambiguous=1 if drop==1` `. replace ambiguous=1 if drop==1 (80 real changes made) .`
	328
	329	`* keep only variables that are needed for further analyses`
▼	330	`keep t t_orig t_new t_new_string mu_orig mu_new mu_new_string sd_new sd_new_string sd_orig RCT DID IV RDD year unique_j experience_avg experience_avg_sq share_top_authors share_top_phd ireport authored_solo share_female_authors editor_present journal_article_cluster FINANCE MACRO_GROWTH GEN_INT EXP DEV LABOR PUB URB sign_5pct aw sign_10pct sign_1pct fstat journal title table method report article journal_name top5` keep t t_orig t_new t_new_string mu_orig mu_new mu_new_string sd_new sd_new_string sd_orig RCT DID IV RDD year unique_j experience_avg experience_avg_sq share_top_authors share_top_phd ireport authored_solo share_female_authors editor_present journal_article_cluster FINANCE MACRO_GROWTH GEN_INT EXP DEV LABOR PUB URB sign_5pct aw sign_10pct sign_1pct fstat journal title table method report article journal_name top5 . keep t t_orig t_new t_new_string mu_orig mu_new mu_new_str > ing sd_new sd_new_string sd_orig RCT DID IV RDD year unique_j experience_avg > experience_avg_sq share_top_authors share_top_phd ireport authored_solo share > _female_authors editor_present journal_article_cluster FINANCE MACRO_GROWTH G > EN_INT EXP DEV LABOR PUB URB sign_5pct aw sign_10pct sign_1pct fstat journal > title table method report article journal_name top5 .
	331
	332	`* label variables that have no label`
▼	333	`label variable year "Year"` `. label variable year "Year" .`
▼	334	`label variable top5 "Published in Top 5 journal"` `. label variable top5 "Published in Top 5 journal" .`
▼	335	`label variable sign_5pct "significant at 5% level"` `. label variable sign_5pct "significant at 5% level" .`
▼	336	`label variable sign_1pct "significant at 1% level"` `. label variable sign_1pct "significant at 1% level" .`
▼	337	`label variable sign_10pct "significant at 10% level"` `. label variable sign_10pct "significant at 10% level" .`
▼	338	`label variable share_top_authors "share of authors share of authors affiliated with top institutions"` `label variable share_top_authors "share of authors share of authors affiliated with top institutions" . label variable share_top_authors "share of authors share o > f authors affiliated with top institutions" .`
▼	339	`label variable share_top_phd "share of authors who completed a PhD at a top institution"` `label variable share_top_phd "share of authors who completed a PhD at a top institution" . label variable share_top_phd "share of authors who complet > ed a PhD at a top institution" .`
▼	340	`label variable share_female_authors "share of female authors"` `label variable share_female_authors "share of female authors" . label variable share_female_authors "share of female autho > rs" .`
▼	341	`label variable journal "Journal"` `. label variable journal "Journal" .`
▼	342	`label variable journal_article_cluster "Article ID"` `. label variable journal_article_cluster "Article ID" .`
▼	343	`label variable experience_avg "Average experience since authors' phds in years"` `label variable experience_avg "Average experience since authors' phds in years" . label variable experience_avg "Average experience since au > thors' phds in years" .`
▼	344	`label variable experience_avg_sq "Average experience since authors' phds in years (squared)"` `label variable experience_avg_sq "Average experience since authors' phds in years (squared)" . label variable experience_avg_sq "Average experience since > authors' phds in years (squared)" .`
▼	345	`label variable editor_present "Editor of an economic journal among authors"` `label variable editor_present "Editor of an economic journal among authors" . label variable editor_present "Editor of an economic journ > al among authors" .`
▼	346	`label variable aw "Weights mapping the inverse number of tests per article"` `label variable aw "Weights mapping the inverse number of tests per article" . label variable aw "Weights mapping the inverse number of t > ests per article" .`
▼	347	`label variable authored_solo "Solo authorship"` `. label variable authored_solo "Solo authorship" .`
▼	348	`label variable DEV "Field: Development Economics"` `. label variable DEV "Field: Development Economics" .`
▼	349	`label variable URB "Field: Urban Economics"` `. label variable URB "Field: Urban Economics" .`
▼	350	`label variable FINANCE "Field: Finance"` `. label variable FINANCE "Field: Finance" .`
▼	351	`label variable LABOR "Field: Labor Economics"` `. label variable LABOR "Field: Labor Economics" .`
▼	352	`label variable PUB "Field: Public Economics"` `. label variable PUB "Field: Public Economics" .`
▼	353	`label variable MACRO_GROWTH "Field: Macroeconomics "` `. label variable MACRO_GROWTH "Field: Macroeconomics " .`
▼	354	`label variable GEN_INT "Field: General Interest"` `. label variable GEN_INT "Field: General Interest" .`
▼	355	`label variable EXP "Field: Experimental Economics"` `. label variable EXP "Field: Experimental Economics" .`
▼	356	`label variable DID "Method: Difference-in-Differences"` `. label variable DID "Method: Difference-in-Differences" .`
▼	357	`label variable IV "Method: Instrumental Variables"` `. label variable IV "Method: Instrumental Variables" .`
▼	358	`label variable RDD "Method: Regression Discontinuity Design"` `label variable RDD "Method: Regression Discontinuity Design" . label variable RDD "Method: Regression Discontinuity Desig > n" .`
▼	359	`label variable RCT "Method: Randomized Control Trial"` `. label variable RCT "Method: Randomized Control Trial" .`
▼	360	`label variable report "Which statistics reported"` `. label variable report "Which statistics reported" .`
▼	361	`label variable ireport "Which statistics reported"` `. label variable ireport "Which statistics reported" .`
	362
▼	363	`saveold mm_data_ready, replace` `. saveold mm_data_ready, replace (saving in Stata 13 format) (FYI, saveold has options version(12) and version(11) that write files in older Stata formats) file mm_data_ready.dta saved .`

Do files for "Methods Matter: p-Hacking and Publication Bias in Causal Analysis in Economics: Comment"