Greetings,
I am interested in estimating an endogenous treatment effects model of the
form:
y = X*Beta + d*Alpha + e
d = I(Z*Gamma + v > 0)
y is continuous although I am also interested in using discrete and count
data as well.
I am trying to estimate a first-stage probit and create the generalized
(probit) residuals to include as a correction term in a second-stage OLS
regression. Does anyone know any Stata programs that will create the
generalized residuals?
Also, does anyone have experience with a multinomial logit or probit (4
choices) first-stage and creating generalized residuals as control
functions?
Thanks for any help,
Mike Furukawa
*
* 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/
