Statalist The Stata Listserver


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

Re: st: xtlogit gllamm


From   Joseph Coveney <jcoveney@bigplanet.com>
To   Statalist <statalist@hsphsun2.harvard.edu>
Subject   Re: st: xtlogit gllamm
Date   Tue, 14 Nov 2006 23:41:20 +0900

Somsupa Nopprach wrote:

 I wonder that is there any different in running
random coefficient logit model by using -xtlogit- and
using -gllamm- command?

--------------------------------------------------------------------------------

Roger Harbord and Alexander Staus have already given some advice about the
greater generality of -gllamm-.  Let me just add that, when you're working
with these nonlinear models, you'll want to use *adaptive* Gauss-Hermite
quadrature.  -xtlogit- and -gllamm- use different implementations of
adaptive Gauss-Hermite quadrature.  As I recall (the posts are on the List
within the past year), -gllamm-'s implementation is somewhat slower but more
accurate than -xtlogit-'s.  StataCorp was looking into this matter at last
report.

Joseph Coveney

*
*   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