The default -predict- option for -probit- is pr, the probability of a
positive outcome. The default for predict after -ivprobit- is xb, the
linear prediction. Take a look at [R] probit postestimation and [R]
ivprobit postestimation. -mfx- uses the default predict option unless you
tell it otherwise. See [R] mfx for more details.
If you want the marginal effects of the probability of positive outcome
after -ivprobit- you need to use the -predict()- option: (as in my examples)
-mfx, predict(p)-
Scott
*
* 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/
