Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | jl591164@albany.edu |
To | statalist@hsphsun2.harvard.edu |
Subject | st: what is the best model fit statistic for multilevel longistic model based on imputed data |
Date | Wed, 15 Sep 2010 12:20:43 -0400 (EDT) |
Dear Statalist, I have five multiple imputed data sets and fitted three level random intercept logistic model with -mim:gllamm-command. The mim:gllamm output does not include any model fit statistics. Does anyone know what is the best model fit statistic for such models and how to get the statistics? I am thinking of log likelihood. I can get log likelihood for a model based on each of the five data set separately, is there a way to combine the log likelihood based on each of the five data set into one likelihood? Thank you very much. Junqing * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/