Maybe you can download -cmp- from SSC! I quote from the help:
"cmp's modeling framework therefore embraces [...] in
principle even regress, sureg, and ivreg / ivregress, as well as the
user-written triprobit, mvprobit, bitobit, mvtobit, and (in its non-endogenous
mode} bioprobit. It goes beyond them in several ways.
[...] And cmp allows the model to vary by observation.
Equations can have different but overlapping samples."
Nicola
At 02.33 05/06/2008 -0400, "Mingfeng Lin" wrote:
>Greetings!
>
>I have two models with the same independent variables (different
>dependent variables, obviously). One equation is a probit model, and
>the other an ordinary least squares. Can anyone give me some
>suggestions on how to estimate these two equations simultaneously,
>similar to SUR?
>
>If I understand correctly, the -sureg- in Stata applies to two
>ordinary least squares models, while the -biprobit- works on two
>probit models. -mvreg- also seems to be designed for two ordinary
>least squares equations. What should I do if I want to estimate two
>equations with different functional forms simultaneously?
>
>Thank you very much for any suggestions!
*
* 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/
