Dear Julia and Statalisters
On 03-31-2004 there was a message by Sophia Rabe-Hesketh mentioning that it
is possible to estimate Random Parameter Logits (or Mixed Logits or error
components logits) using gllamm in Stata. (Message below)
I have read GLLAMM Manual and think this is the case, though I may be wrong.
I am very interested on this topic (remember the desperate Ph.D Candidate
who wants to graduate) so I would appreciate any thoughts
Thanks a lot in advance
Adrian
From: [email protected]
[mailto:[email protected]] On Behalf Of Sophia
Rabe-Hesketh
Sent: Wednesday, March 31, 2004 12:57 AM
To: [email protected]
Subject: Re: st: RE: Re: Random Parameter Logit
Adrian,
You can estimate these models in gllamm as well, using adaptive quadrature,
see:
http://www.gllamm.org
We have a paper on these models (where
estimation was done using gllamm):
Skrondal, A. and Rabe-Hesketh, S. (2003).
Multilevel logistic regression for polytomous data and rankings.
Psychometrika 68 (2), 267-287.
Sophia
*
* 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/
