My understanding is that the missing LR / Wald test statistics means
that Stata did not know what to compare this model to, which in this
case would be a model with constant term only. The reason it appears
is because the -ml- output is unified, although not every model that
can be fit with it really admits a null model of the constant-only
type. E.g. in the panel data case, should you assume all slopes are
equal to 0, or should you assume that not only all slopes are = 0, but
also the random effect variance is 0 for your null model?
--
Stas Kolenikov
http://stas.kolenikov.name
*
* 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/
