----------------------------------------------------------------------
Date: Thu, 19 Oct 2006 17:48:32 +1000
From: Garry Anderson <[email protected]>
Subject: st: sureg and logistic regression
Seemingly Unrelated Regression
- -sureg- is designed for linear regression analysis.
However, can it be adapted and used for logistic regression?
Regards, Garry
----------------------------------------------------------------------
-
Seemingly unrelated regression for models with binary dependent
variables is not straightforward, especially in the logistic case.
It's more straightforward for probit models, as one can use the
multivariate normal distribution.
For the 2 binary outcomes case, use -biprobit-. For >=2 binary
outcomes case, use -mvprobit-, which uses maximum simulated likelihood
estimation (MSL). The latest version is downloadable from the Stata
Journal site (vol 6, no. 2), accessible via the Stata Help menu.
Note that the Cappellari and Jenkins article in the same SJ issue also
provides alternative means of estimating multivariate probit models by
MSL. We provide some illustrative ado file code, and there is a Stata
plug-in, so for problems with large data sets or many dimensions,
there are big speed savings. A pre-print of our SJ article is
available as an ISER working paper (link from URL below).
Stephen
-------------------------------------------------------------
Professor Stephen P. Jenkins <[email protected]>
Institute for Social and Economic Research
University of Essex, Colchester CO4 3SQ, U.K.
Tel: +44 1206 873374. Fax: +44 1206 873151.
http://www.iser.essex.ac.uk
Survival Analysis using Stata:
http://www.iser.essex.ac.uk/teaching/degree/stephenj/ec968/
Downloadable papers and software: http://ideas.repec.org/e/pje7.html
*
* 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/
