Statalist


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

RE: st: gllamm vs xtlogit results


From   "Anderson, Bradley J" <BAnderson1@lifespan.org>
To   <statalist@hsphsun2.harvard.edu>
Subject   RE: st: gllamm vs xtlogit results
Date   Tue, 5 Feb 2008 08:57:01 -0500

Wanted to thank Jean Marie, Austin Nichols, and Hind Sbihi for their helpful comments.  Since yesterday I've learned that the data I'm working with probably require a large number of integration points; the intraclass correlation is quite high and the average number of level 1 observations per group is 87.5.  Even models estimating only a constant and the random effect were not converging until a large number of integration points had been specified.  I also think I need to re-think model specification cause when I think about the data the assumption that the X are not associated with the random effect is not reasonable, especially for one of the predictors.  Thanks again for the very useful comments.

Brad


*
*   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