My name is Fabio Berton, from Italy; I want to estimate a probit (or logit)
model using (among others) an endogenous regressor (actually wage),
according to Richard Blundell's method, which suggests to run OLS on the
endogenous variable and a set of exogenous ones, and then to use estimated
residuals to capture the effect of endogeneity in the non linear model; how
can I do that with Stata? I looked at the new Stata 8 "qvf" command: is
that a good choice? How does that command works (i.e. which statistical
method uses to get the estimates)? Thanks a lot.
Fabio.
*
* 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/
