I have missed out on the beginning of the thread. But if you have 13
predictor variables, I thought that the rule of thumb was to have a minimum
of 20 observations per parameter for log-linear models. Your low sample size
might be causing instability.
With regards
Dr Adrian Esterman
Senior Research Fellow
Department of General Practice
Flinders University
(08) 8204 4617
*
* 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/
