st: re: My dependent variable is a dummy, and I have endogenous variable among the regressors, so I have to use "ivprobit". How should I do relevance test and overidentifying test under this condition? How could I check my instrument is uncorrelated to the error (is valid) and is relevant to the endogenous variable (is relevant)? Does STATA has some command like "ivreg2" for "ivprobit"?

[Kit Baum <baum@bc.edu>]

Yan wrote

My dependent variable is a dummy, and I have endogenous variable among
the regressors, so I have to use "ivprobit". How should I do relevance
test and overidentifying test under this condition? How could I check my
instrument is uncorrelated to the error (is valid) and is relevant to
the endogenous variable (is relevant)? Does STATA has some command like
"ivreg2" for "ivprobit"? Thank you very much for help.


Two answers:

1) you can use -ivreg2- on this model, which will yield consistent  
(if not efficient) estimates, and give you access to all the panoply  
of tests in that program. Please see my UKSUG2007 talk at

http://ideas.repec.org/p/boc/usug07/12.html

2) You may use -overid- (findit overid) to perform the overid test  
after ivprobit with the twostep option.


Kit Baum, Boston College Economics and DIW Berlin
http://ideas.repec.org/e/pba1.html
An Introduction to Modern Econometrics Using Stata:
http://www.stata-press.com/books/imeus.html


*
*   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/