Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: bivariate ordered probit / ordinal probit - ctd.


From   Thomas Cornelißen <cornelissen@mbox.iqw.uni-hannover.de>
To   "Joseph Coveney" <jcoveney@bigplanet.com>, "Statalist" <statalist@hsphsun2.harvard.edu>
Subject   Re: st: bivariate ordered probit / ordinal probit - ctd.
Date   Mon, 7 Nov 2005 17:02:13 +0100

Thanks a lot to Joseph for these very helpful responses ! This way it should
work out to implement a bivarite ordered probit model.

I think another way to estimate a bivariate ordered probit model would be to set up the likelihood function of a two-equation bivariate ordered probit model in Statas ML-routine, using the bivariate normal cdf which is available in Stata. The likelihood function would be a generalization of the likelihood function of -biprobit- to several categories.

I suppose this would be quicker than using -gllamm- or -reoprobit-, because it would not rely on quadrature (if I get that right).

Is anybody aware of an existing do-file for this model ?
Thomas


-------------------------------------------------------------------------
Thomas Cornelissen
Institute of Empirical Economic Research
University of Hannover, Germany
cornelissen@mbox.iqw.uni-hannover.de
*
* 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