There's some stuff like -biprobit- and -heckprob- that you might want
to check out, as well as a host of probit IV implementations (I
remember vaguely that there were two or even three of them under the
names like -ivprob- and/or -probitiv- and/or -ivprobit-, and there's
been some discussion on statalist which one is better, but I don't
think I remember what the conclusion was). I would just put this stuff
into -gllamm-.
Note that if you don't have any extra excluded variables/instruments
in your regression for the endogeneous explanatory variable, then the
model is identified only due to non-linearity of the inverse Mills'
ratios, and nobody will buy a model like that for a serious research.
On Mon, 14 Feb 2005 03:00:08 -0800 (PST), bhagirath behera
<[email protected]> wrote:
> Dear all,
> Does anyone have any idea how to solve the endogeneity
> problem in a logit model? I have a explanatory
> variable which is dichotomous and determined by few
> other variables that are also present in the same
> model as explanatory variables.
> Thanks alot.
> Bhagirath
>
> =====
> Bhagirath Behera
> Center For Development Research (ZEFb)
> Walter-Flex-Str.3,
> 53113, Bonn, Germany
> Phone: 0049- 228- 731728 (office)
>
> http://www.zef.de
>
> __________________________________________________
> Do You Yahoo!?
> Tired of spam? Yahoo! Mail has the best spam protection around
> http://mail.yahoo.com
> *
> * For searches and help try:
> * http://www.stata.com/support/faqs/res/findit.html
> * http://www.stata.com/support/statalist/faq
> * http://www.ats.ucla.edu/stat/stata/
>
--
Stas Kolenikov
http://stas.kolenikov.name
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
