Rosa Maria,
to your second question; the hausman is based on the difference between the
coefficients of the RE and the FE model to test the H0: E(unobserved|
expl.vars)=0 . So in principle your test result indicates that you cannot
reject the H0 and thus the RE.
Jesper
----- Original Message -----
From: <[email protected]>
To: <[email protected]>
Sent: Monday, May 26, 2003 10:30 AM
Subject: st: Pooled vs. RE
> Dear all,
> I am trying to compare pooled, random effects and fixed effects models.
> I would like to know what test to use to test the specification between
> OLS and random effects.
> I also would like to know why in a Hausman test I get a statistic value
> 0 with probability 1, is this possible? what is the interpretation?
>
> Thank you in advance,
> Rosa Maria Martin.
>
>
>
>
> *
> * 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/
>
>
*
* 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/
