st: biprobit/mvprobit and unobserved heterogeneity

[Dimitrije Tišma <dimitrijetisma@gmail.com>]

Dear all,

I am very far from being a good and experienced Stata programmer, so
this question is a very general one and may seem very basic to some of
you. Using a duration discrete-time model I am trying to jointly
estimate the factors affecting transition into and out of
unemployment.  In most recent papers that have dealt with the issue of
unobserved heterogeneity in the context of state transitions (e.g.
poverty status transition) the authors do this joint estimation but
they also estimate parameters that account for the unobserved
heterogeneity as well as the share of population that each of these
parameters comprises. I have used biprobit and mvprobit, but as far as
I know these commands do not have options that go that far as to
estimate these parameters. I suppose that some refined -ml-
programming is unavoidable? All the best and thanks in advance!
*
*   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/