Re: st: marginal effects after ivprobit

["Gandelman, Nestor" <gandelman@ort.edu.uy>]

Hi,
I finally guessed what was going on and how to solve it. Sorry for if
If someone cares to know my problem was that the ivprobit assumes xb as 
the default for predict while the probit assumes the p option as its 
default. That's why to estimate the marginal effect of obtaining a 
positive outcome it is enough to type mfx after a probit model, but 
after ivprobit it is necessary to specify: mfx compute, predict(p).
Why the default for predict is different in the probit and ivprobit command?
Best, Nestor


Gandelman, Nestor escribi�:


> Hello statalisters,
> I'm using the ivprobit command to estimate probit model with one 
> endogenous regressor.
> The mfx (and mfx2) packages reported marginal effects are the same as 
> the output coefficients.
> This seems not to be right or I'm missing something?
> Best, 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/
*
*   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/