Yes, I agree, It is biprobit with a restriciton of rho being zero so
it becomes like a univariate probit.
I now read your suggested link but still don't understand the following:
"If you want to force mfx to compute a marginal effect, despite
failing the above test, you can do so by using the force option. But
remember that mfx is operating under the assumption that it does not
matter which observation it predicts into, and since it has to predict
somewhere, it is predicting into observation 1 of the e(sample). "
Thanks,
Nirina
On 10/18/07, Austin Nichols <[email protected]> wrote:
> Nirina--
> It seems that, contrary to your first post, your problem arises not from
> running -probit- followed by -mfx- but from running -biprobit-
> followed by -mfx-.
> Have you read
> http://www.stata.com/support/faqs/stat/mfx_unsuit.html
> yet?
>
> On 10/18/07, Nirina F <[email protected]> wrote:
> > Ok Nick, this is a bit of details.
> > I am mainly looking at the impact of binge drinking on violence
> > related outcomes.
> > I run probit but then biprobit. And I have controls such as age, sex, race,
> > ethnicity, religious affiliation, year in school, parents education,
> > parents drinking patterns, living arrangements,type of college,
> > region, and year.
> > So as I said below, I have to force -mfx- to give me s.e but then
> > these s.e would not even be reported in estout. And what are the
> > costs of this -force-?
> *
> * 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/
