st: Multivariate Tobit

["Diana Fletschner" <fletschn@u.washington.edu>]

Dear Stata-users:

I am trying to analyze how spouses who save structure their savings 
portfolio. That is, what percentage of their savings is in joint accounts, 
or under his name, or under her name. A basic approach would be to use three 
Tobit models given that the three dependent variables are bounded between 0 
and 100. However, I want to estimate them jointly as a Multivariate Tobit 
given that the errors are likely to be correlated due to unobserved 
household characteristics. And, I would like to impose restrictions on the 
coefficients taking advantage of the fact that we know the sum of the three 
dependent variables has to equal 100.

Does anyone have and is willing to share a routine to do the Multivariate 
Tobit (ideally with upper and lower limits and with restrictions) ?  Or any 
suggestions on how to proceed?

I would appreciate any help!
Diana

_________________________________
Diana Fletschner
Assistant Professor
Daniel J. Evans School of Public Affairs
University of Washington
(206) 616-1297



*
*   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/