Dear Listers,
I have a dumb question about the estimation of time fixed or random effects
in panel-related commands in Stata (9). I have a feeling that the fixed or
random effects are treated explicitly only for the cross-section part, not
for the time dimension, in maybe all the commands. Am I right? Time fixed
effects seems to be done by adding time dummies. It's easy but again am I
missing an existing option, function in a command? In addition, when I want
to estimate something like cross-section fixed, time random model or the
reverse, I need some help on this too.
What I found is the xtmixed command may be capable of dong this. I'm not
sure. But it seems that all other great commands, such as xtabond, xtabond2,
and all families of xtreg (continuous, logit, probit, mlogit, etc) do not
have this explicitly (especially for time random effects or mixed effects).
Besides, xtmixed uses ML estimation and there is no GMM counterpart. I must
be missing something. Thank you for your help in advance.
Wanli Zhao
*
* 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/
