Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: mvprobit


From   Charlotte Gary <charlottegary83@yahoo.com>
To   owner-statalist@hsphsun2.harvard.edu
Subject   st: mvprobit
Date   Sun, 5 Jul 2009 15:12:55 -0700 (PDT)

Hi all,
here is my problem:
I'm estimating a multivariate probit using mvprobit (with 3 equations).

I would like to estimate of the predicted probabilities of every
possible outcome after estimation.

Of course this is an easy task using the postestimation command
mvppred when the purpose is to estimate the  success probability for
each equation - i.e. (1, 0, 0), (0, 1, 0), and (0, 0, 1) or to estimate all
ones/all zeros cases (1, 1, 1), (0, 0, 0) using pall.

However, it is not clear to me how to compute the probabilities of the
all the other possible multiple outcomes - i.e. (1, 1, 0), (1, 0, 1) and (0,
1, 1).  I realize that the paper of Cappellari and Jenkins 2006 should
be informative on this issue. However, it is not completly clear to
me how to use mvnp() after a mvprobit and then estimate these
probabilities. 

Does anyone have any idea or  suggestions? Is it
possible to use mvpn() after mvprobit? I cannot find a
specific example in the 2006 paper of such a case

I apologize in advace if this issue was alredy discussed before...

thanks
Charlotte



      


*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index