Hi,
I am running an xtreg with Random Effects, and would like to perform
something like an incremental F-test to test if models improve
significantly.
Which of the reported R-squares should I be using for the F-test?
(within, between, overall?). Also, as I am counting the number of
independent variables, am I right to assume that the random effect is
like a fixed effect in the sense that it simply can be counted as one
variable (i.e., a dummy except with random values) per group?
Finally, is there an alternative test that is superior and that I should
be using instead?
Thanks,
Ann
*
* 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/
