I am estimating a GLM model, using family(gamma) link(identity)
It is a large model: >8000 observations. I am doing some LL ratio tests
to test significance of sets of variables, and what is surprising is
that removing sets of variables which have very high individual z
statistics lead to negligible changes in the reported LL value.
I am wondering why this might be.
Michael
*
* 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/
