Hi everybody,
I would like to estimate a probit model of the follwing form
Y1= Y2 X1 X2
where Y2 is an endogenous dummy variable.
Will the ivprob routine help me?
What if I implement a "recursive form" using biprobit
The model I've in mind is:
Y1= Y2 X1 X2
Y2= X2 X3
can this be implemented with: biprob (Y2=X2 X3) (Y1= Y2 X1 X2)?
Alternatively I can estimate a system of ecuations with two probits:
Y1= Y2 X1 X2
Y2= Y1 X2 X3
Does biprobit work well in this case? Any other suggestions?
I appreciate any help on this matters!!
Nestor
*
* 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/
