Dear All,
I posted earlier but made it more complicated than necessary and did not get any response. So, trying again.
I want to bootstrap my standard errors for a two step estimation procedure but am getting an error message. Here is the dataex for my data:
I want to run a 2-step estimation, which runs smoothly without bootstrapping for standard errors:
I clearly have a relatively large sample size, but, when I bootstrap standard errors to account for the two step estimation, I get the following error message:
What am I doing wrong here? Will be grateful for your input.
Sincerely,
Sumedha
I posted earlier but made it more complicated than necessary and did not get any response. So, trying again.
I want to bootstrap my standard errors for a two step estimation procedure but am getting an error message. Here is the dataex for my data:
Code:
* Example generated by -dataex-. For more info, type help dataex clear input float grpatidtreat byte(Female age80plus Asian Black Hispanic) float COVID double PopDensity float tavg double prcp byte(_st _d _t _t0) 15206 0 0 0 1 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 3004 1 0 0 1 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 17435 0 0 0 1 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 2112 1 1 0 1 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 26240 0 0 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 19463 0 0 0 1 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 20156 0 0 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 1578 1 1 0 1 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 20172 0 0 0 1 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 19990 0 1 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 24292 1 0 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 22231 1 1 0 1 0 0 99.2 26.89387 102.04999969899654 1 1 1 0 3816 0 0 0 1 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 1326 1 0 0 1 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 25147 0 0 0 1 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 24294 0 0 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 6048 0 0 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 20208 1 1 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 12468 1 0 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 24929 1 0 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 18131 0 1 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 8075 0 0 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 18614 1 0 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 1100 1 1 0 1 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 20014 1 1 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 20349 1 1 0 1 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 15241 1 0 0 1 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 8237 0 0 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 347 1 1 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 532 1 0 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 20100 1 0 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 7709 1 1 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 21965 1 0 0 1 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 245 0 0 0 1 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 12819 0 1 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 26574 0 0 0 1 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 22608 1 1 0 1 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 20670 0 0 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 10468 1 0 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 2431 1 1 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 22729 1 0 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 19918 1 1 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 6767 0 0 0 1 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 2013 1 1 0 1 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 13247 0 0 0 1 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 409 0 0 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 24019 1 1 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 8130 1 1 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 1503 1 1 0 1 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 450 0 0 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 25712 0 0 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 21945 1 0 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 7870 1 0 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 19688 0 0 0 1 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 22838 1 0 0 1 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 26055 0 0 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 6305 1 0 0 1 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 2688 1 1 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 7771 0 0 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 21690 1 0 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 24805 1 0 0 1 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 22742 0 0 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 5887 0 0 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 14911 0 0 0 1 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 10076 0 0 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 19660 1 1 0 1 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 23040 1 0 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 1188 0 0 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 18448 0 0 0 1 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 7966 0 0 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 2058 0 0 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 693 1 1 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 338 0 1 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 1245 0 1 0 1 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 25259 1 0 0 1 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 22337 0 0 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 21719 0 0 0 1 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 21801 0 0 0 1 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 19906 0 0 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 2593 1 0 0 1 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 10784 1 1 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 7057 0 0 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 22519 1 0 0 1 0 0 99.2 26.89387 102.04999969899654 1 1 1 0 22109 0 0 0 0 1 0 99.2 26.89387 102.04999969899654 1 0 1 0 1508 0 0 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 24739 0 0 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 19928 1 0 0 1 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 22893 1 0 0 1 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 19535 1 0 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 22551 1 0 0 1 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 10009 0 0 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 1990 1 0 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 14715 1 0 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 8545 0 0 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 24844 0 0 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 20016 1 1 0 0 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 21723 1 0 0 1 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 20133 0 1 0 1 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 7299 1 0 0 1 0 0 99.2 26.89387 102.04999969899654 1 0 1 0 24604 0 0 0 0 1 0 99.2 26.89387 102.04999969899654 1 0 1 0 end label values COVID COVID label def COVID 0 "No confirmed COVID-19", modify
Code:
. probit COVID Female age80plus Asian Black Hispanic PopDensity tavg prcp if sample==1 Iteration 0: Log likelihood = -84773.888 Iteration 1: Log likelihood = -84145.633 Iteration 2: Log likelihood = -84139.719 Iteration 3: Log likelihood = -84139.718 Probit regression Number of obs = 697,196 LR chi2(8) = 1268.34 Prob > chi2 = 0.0000 Log likelihood = -84139.718 Pseudo R2 = 0.0075 ------------------------------------------------------------------------------ COVID | Coefficient Std. err. z P>|z| [95% conf. interval] -------------+---------------------------------------------------------------- Female | .024962 .006397 3.90 0.000 .012424 .0375 age80plus | -.1059373 .0076874 -13.78 0.000 -.1210044 -.0908702 Asian | .0091485 .0177039 0.52 0.605 -.0255504 .0438474 Black | .0673043 .0105328 6.39 0.000 .0466603 .0879483 Hispanic | .2271459 .0092874 24.46 0.000 .2089429 .245349 PopDensity | .0001692 .0000121 14.04 0.000 .0001455 .0001928 tavg | -.0063606 .0003474 -18.31 0.000 -.0070415 -.0056797 prcp | .0001733 .0000623 2.78 0.005 .0000512 .0002954 _cons | -1.933265 .0082191 -235.22 0.000 -1.949374 -1.917156 ------------------------------------------------------------------------------ . . //margins, dydx(*) . predict xd2h, index . gen phi2h = normalden(xd2h) . gen PHI2h = normal(xd2h) . gen gr2 = COVID*phi2h/PHI2h - (1 - COVID)*phi2h/(1 - PHI2h) . gen COVID_gr2 = COVID*gr2 . . . foreach v in Female age80plus Asian Black Hispanic { 2. sum `v' 3. gen `v'm=`v'-r(mean) 4. gen COVID_`v'm=COVID*`v'm 5. gen COVID`v'gr2=COVID_`v'm*gr2 6. } Variable | Obs Mean Std. dev. Min Max -------------+--------------------------------------------------------- Female | 697,605 .5619885 .4961429 0 1 Variable | Obs Mean Std. dev. Min Max -------------+--------------------------------------------------------- age80plus | 697,605 .2472932 .4314389 0 1 Variable | Obs Mean Std. dev. Min Max -------------+--------------------------------------------------------- Asian | 697,605 .0342801 .181948 0 1 Variable | Obs Mean Std. dev. Min Max -------------+--------------------------------------------------------- Black | 697,605 .0990632 .2987471 0 1 Variable | Obs Mean Std. dev. Min Max -------------+--------------------------------------------------------- Hispanic | 697,605 .1089069 .3115226 0 1 . . ***Second Stage*** . eststo: stcrreg Female age80plus Asian Black Hispanic COVID gr2 if sample==1, compete(d2=2) Failure _d: d2==1 Analysis time _t: stop Enter on or after: time start ID variable: grpatidtreat Iteration 0: Log pseudolikelihood = -37079.611 Iteration 1: Log pseudolikelihood = -37077.898 Iteration 2: Log pseudolikelihood = -37077.897 Competing-risks regression No. of obs = 697,196 No. of subjects = 25,644 Failure event: d2 == 1 No. failed = 3,737 Competing event: d2 == 2 No. competing = 2,261 No. censored = 19,646 Wald chi2(7) = 1227.46 Log pseudolikelihood = -37077.897 Prob > chi2 = 0.0000 (Std. err. adjusted for 25,644 clusters in grpatidtreat) ------------------------------------------------------------------------------ | Robust _t | SHR std. err. z P>|z| [95% conf. interval] -------------+---------------------------------------------------------------- Female | 1.095094 .0366405 2.71 0.007 1.025584 1.169315 age80plus | 3.00898 .1062511 31.20 0.000 2.807775 3.224604 Asian | .9216742 .0904136 -0.83 0.406 .7604611 1.117063 Black | 1.128179 .0618504 2.20 0.028 1.01324 1.256156 Hispanic | 1.237449 .0724726 3.64 0.000 1.103255 1.387966 COVID | .0949024 .1989416 -1.12 0.261 .0015593 5.776043 gr2 | 3.251186 2.834039 1.35 0.176 .5889177 17.94854 ------------------------------------------------------------------------------ (est47 stored) . estimates store ProbitCF
Code:
. ***First Stage*** . probit COVID Female age80plus Asian Black Hispanic PopDensity tavg prcp if sa > mple==1 2. predict xd2h, index 3. gen phi2h = normalden(xd2h) 4. gen PHI2h = normal(xd2h) 5. gen gr2 = COVID*phi2h/PHI2h - (1 - COVID)*phi2h/(1 - PHI2h) 6. gen COVID_gr2 = COVID*gr2 7. . foreach v in Female age80plus Asian Black Hispanic { 8. sum `v' 9. gen `v'm=`v'-r(mean) 10. gen COVID_`v'm=COVID*`v'm 11. gen COVID`v'gr2=COVID_`v'm*gr2 12. } 13. . ***Second Stage*** . eststo: stcrreg Female age80plus Asian Black Hispanic COVID gr2 if sample==1, > compete(d2=2) . end . . bootstrap _b, reps(100) seed(123): boot (running boot on estimation sample) Bootstrap replications (100): xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx > xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx done x: Error occurred when bootstrap executed boot. insufficient observations to compute bootstrap standard errors no results will be saved r(2000); end of do-file r(2000);
What am I doing wrong here? Will be grateful for your input.
Sincerely,
Sumedha
