[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
Re: st: Is there a way of testing for endogeneity in probit models (to rule out simultaneous equations)?
If Y is binary and X3 is linear, you can use the Blundell-Smith exogeneity
test as given in the probexog.ado file (this test can be specified after
the ivprob and divprob ado files).
> I would like to test whether the probit model:
> Y = a0 + a1X1 + a2X2 + a3X3 + e1
> has an endogeneity problem, and should instead be
> treated as a system of equations, where
> X3 = b0 + b1X1 + b2X2 + e2
> As far as I have understood, both the Hausman IV test
> and the Davidson/MacKinnon augmented regression test
> only apply for OLS???
> Is there any method of testing for endogeneity in
> probit models???
> I'd be greatful for any tips...
> many thanks, Annette
> Do You Yahoo!?
> Yahoo! Finance - Get real-time stock quotes
> * 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/
Lisa M. Powell <email@example.com>
School of Policy Studies, Tel 613-545-6692
Queen's University, Fax 613-545-2135
K7L 3N6, Canada
* For searches and help try: