> I have two fixed effect panel regressions. I want to test the equality
> of the two fixed effects using an F-test, but I cannot seem to do this. I
> have obtained the predicted values of the fixed effects through the
> command:
>
> predict fe1, u
> predict fe2, u
>
> I have tried to test these through the "test" command, but that doesn't
> seem to be working. Any help is greatly appreciated.
Do you want to test the fixed effects themselves, or the coefficients from
two fixed effect regressions? I don't think that testing the fixed effects
themselves is a very good idea, as long as those are not consistently
estimated in a usual panel setting (short T, many N). If you are really
curious, you can do any sort of a paired tests -- see -ttest- or
-signrank-. I'd trust the latter to a greater extent. Also, make sure you
are using only one observation per panel. Those tests would not account
for the fact that you have estimated the fixed effects -- essentially, you
are using one degree of freedom per observation, so formally you don't
have any degrees of freedom to conduct those tests. That's the consequence
of the lack of estimability.
--- Stas Kolenikov
-- Ph.D. student in Statistics at UNC-Chapel Hill
- http://www.komkon.org/~tacik/ -- [email protected]
* This e-mail and all attachments to it are not intended to provide any
* reasonable point of view and was transmitted to you in error. It
* should be immediately deleted by all recipients unless they really
* enjoy communicating with the author :). Other restrictions apply.
*
* 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/
