See if this helps:
http://www.stata-journal.com/article.html?article=st0018. It discusses
linear regression, but I imagine you could extend it to GMM, as well.
On Wed, Sep 16, 2009 at 4:05 AM, Anselm Mattes <[email protected]> wrote:
> Dear Statalist,
>
> I am trying to estimate a GMM (Blundell-Bond) model where one of my regressors has been estimated by a probit model in a first step. Wooldridge (2002), chap. 6 points out that the estimates are consistent, but standard errors need to be corrected. In appendix 6A (p. 139) he derives the corresponding formulas. Does anybody know, whether this (or another suitable) solution is implemented in Stata? I believe that the heckman (two step) command has built in something like this. Am I right?
>
> I am aware that this question has already been posted, but that was some years ago and there was no solution given at that time.
>
> I appreciate any help!
>
> Best regards,
> Anselm
>
> _________________________________________________________________________
> Anselm Mattes
> Diplom-Ökonom
> Email: [email protected]
> Tel: 07071 - 9896 - 16
> ------
> Institut für Angewandte Wirtschaftsforschung, Tübingen
> Ob dem Himmelreich 1
> 72074 Tübingen
> Tel: 07071 - 9896 - 0
> Fax: 07071 - 9896 - 99
> http://www.iaw.edu
> _________________________________________________________________________
>
>
>
> *
> * 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/
>
--
Stas Kolenikov, also found at http://stas.kolenikov.name
Small print: I use this email account for mailing lists only.
*
* 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/
