RE: st: xtnbreg - robusteness check and model relevance
Date
Thu, 17 Jan 2013 20:31:02 +0100
Dear Mário,
At a first sight I cannot see nothing against performing a simple LR test
since your first model is nested in the second model.
Or, you can simply look to the log likelihood function to conclude that
including
the time controls does indeed improve the fit of you model (the LL value
is higher
as it is the Wald test statistic).
Best,
Andre
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/faqs/resources/statalist-faq/
* http://www.ats.ucla.edu/stat/stata/
