You may download -cmp- from SSC. 90% of the times it's what you are searching for when endogeneity is the problem.
Some more specific programs exist with multinomial variable at the first stage (-selmlog- and -mtreatnb-: if this is the case, please use -findit- to locate them). Not aware of dedicated programs where the multinomial variable is the dependent one at the second stage.
Nicola
P.S. I'll NOT receive/read any email but the Digest.
At 02.33 09/10/2008 -0400, "Martorana, Marco F" wrote:
>Hi everybody,
>I need to run a multinomial (logit or probit) with endogenous regressors. Is there any stata command for using instrumental variables with polychotomous dependent variable?
*
* 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/
