Statalist The Stata Listserver


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

st: Mata ghk and multivariate tobit


From   Emma Stephens <ecs33@cornell.edu>
To   statalist@hsphsun2.harvard.edu
Subject   st: Mata ghk and multivariate tobit
Date   Tue, 11 Jul 2006 09:06:04 -0400

Hello again and thank you for this. I had another question for the list on this topic, which was whether it is possible to estimate a multivariate tobit system using mvnp and mdraws? mdraws seems to just give a scalar from a draw from a multivariate normal random variable, however I think I need to use mdraws to construct the overall likelihood function to run ml....if anyone has any suggestions, please let me know - it looks like I may need to use the ghk utility directly to write into the maximum likelihood function, rather than the new commands, but how do you get the ghk() results out of the mata interface and into your maximum likelihood function? I know others have estimated censored demand systems, which are multivariate tobit system basically, using GAUSS, but I'd like to use Stata!!!

Thanks again
Emma



At 08:03 AM 7/11/2006, you wrote:

Emma Stephens <ecs33@cornell.edu> asked for more information
on using Mata's ghk() function.  The latest Stata Journal is
special issue on maximum simulated likelihood.  There is a paper
on using Mata's ghk() function with an example estimating the
parameters of a multinomial probit model.

Use the -net- command to get access to the examples

. net sj 6-2 st0102

-Rich
rgates@stata.com
*
*   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/
*
*   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/



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