Dear all,
I am doing some regressions on panel data. The thing is that in some of them when i am trying to compute the hausman test apperas the following message: Estimate of sigma u_i = 0, random-effects estimator has degenerated to pooled OLS and the Wald Test from xthausman may not be appropiate. See [R] hausman for a more general implementation of the hausman test. I do not know why such an error. Please, I need an answer soon.
An another question. In order to compare pooled, random and fixed effects models I am using the F statistic in the fixed effects regresion to test it versus pooled, and the Breusch-Pagan estatistic to test the random efects model versus pooled. Is that correct?
Thank you in advance,
Valeriano Martinez San Roman.
*
* 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/
