Hi!
I have a problem with the instrumental variable estimation. It turns out that there are two endogenous variables in a system, but one of then is a dummy variable, and it�s related with the probability of certain event. In normal circumstances, I would estimate this dummy variable by using a probit regression, but because of its endogenous condition, I thought it would be better to estimate the entire system by two-stage least squares. The problem here is just that I�m not sure that using the instrumental variable estimation would be the better solution, because there is a dummy variable involved, and I don�t know a command that could merge the probit estimation of one equation and the least square estimation of the another equation of the system.
Has anybody a recommendation?
Obtenga su E-mail GRATUITO en http://economistasuanl.zzn.com
____________________________________________________________________________________________________________
Para obtener su propio servicio de correo electr�nico basado en la Multimalla, dir�jase a http://www.zzn.com
*
* 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/
