Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Jorge Eduardo Pérez Pérez <perez.jorge@ur.edu.co> |
To | "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu> |
Subject | Re: st: How to combine multiple imputation with reg3 for simultaneous equations |
Date | Mon, 4 Jun 2012 11:49:41 -0400 |
There must be a good reason why -reg3- is not allowed to be used in conjunction with multiple imputation. Probably it is because the standard errors produced by the command will not be correct, since you have to adjust for the generated regressors as well as the imputation. Maybe a robust s.e. estimator can deal with both issues. Having said that, have you tried the -cmdok- option? webuse mheart1s20, clear mi describe reg3 (bmi attack age) (attack smokes age), 2sls mi estimate, cmdok: reg3 (bmi attack age) (attack smokes age), 2sls _______________________ Jorge Eduardo Pérez Pérez On Fri, Jun 1, 2012 at 1:30 PM, Agnete Aslaug Kjær <agnete.kjaer@gmail.com> wrote: > Hi > > First time I write StataList. Hope You can help? > > I do a simultaneous equations model i Stata by using "reg3, 2sls" > > However, I have problems with missing data, so fitst I do multiple > imputations by using "mi" > > How can I make use of the imputed data in reg3? Since "mi estimate" > does not support "reg3" I am in trouble..? > > Best regards, > > Agnete Kjaer > > CPH University > * > * For searches and help try: > * http://www.stata.com/help.cgi?search > * http://www.stata.com/support/statalist/faq > * http://www.ats.ucla.edu/stat/stata/ > > * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/