Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: Multivariate probit postestimation


From   Susan Steiner <steiner@giga-hamburg.de>
To   statalist@hsphsun2.harvard.edu
Subject   st: Multivariate probit postestimation
Date   Mon, 04 Aug 2008 14:53:50 +0200

Dear Statalist users,

We are employing a multivariate probit model for the estimation of three alternative outcomes (use of savings, use of credits, use of insurance). We are using the commands by Capillari and Jenkins but do not know how to produce marginal joint probabilities (and significance levels) for combinations of these alternatives. Capillari and Jenkins provide the commands for producing marginal probabilities for each equation and for joint marginal probabilities for all successes and all failures (mvpred, pall) but not for other combinations of the alternatives (for example, use of savings and insurance but no use of credit). Does anybody have experience with doing bootstrap procedures in this case?
Thanks!
Susan

*
* 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