[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
Re: st: hausman and xthausman after panel fe, re
Alice Dobson <email@example.com> asked on the list,
> I have a similar problem. I obtain this output after using Hausman.
> Since, suest is unavailable after xtreg, can I simply go ahead and
> present the results from xtreg, re?
> . hausman fixed random
> Test: Ho: difference in coefficients not systematic
> chi2(4) = (b-B)'[(V_b-V_B)^(-1)](b-B)
> = -6.22 chi2<0 ==> model fitted on these
> data fails to meet the asymptotic
> assumptions of the Hausman test;
> see suest for a generalized test
I don't really have much to add beyond my earlier long-winded post and what
is said in [R] hausman about negative test statistics,
"In this case the chi-square is actually negative. We might
interpret this as strong evidence that we cannot reject
the null hypothesis."
If Alice really wants a non-negative test statistic (and who doesn't) she
might consider one of the artificial regressions discussed in prior posts.
* For searches and help try: