Dear,
How can I test the significance in model improvement for model 2
versus model 1 when using ML estimation on clustered data?
For both models I am using interval regression (intreg) with the
option "cluster". Since the likelihood ratio test is not valid with
the option cluster (see
http://www.stata.com/support/faqs/stat/lrtest.html), I need a
different test to assess the improvement in goodness of fit.
A Wald chi2 statistics is reported for the model goodness of fit, but
I do not know whether that can be used for comparison across models.
Many thanks,
Bart Vanneste
*
* 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/
