st: sigma_u is zero -xtregar-

[Carmen Blanco <blnco.mc@gmail.com>]

Dear statalist,

I have an unbalanced panel data with AR 1 and I have some problems.

Breusch-Pagan test tell me that the model is not OLS. In fact, it is a
panel data (Particularly it is a random-effects model because Hausman
test confirm me this).

But I´m very confused about why the sigma_u listed in the output from
a random effect model reports a value of zero. So,I have 3 questions:

1) Could someone please tell me what this means?

2) Could someone please tell me how can I generate the significance of
this test from xtregar estimation?

3) And could someone please tell me why in the random effects model
does not generate a F test to check the significance of this test?

Thanks

Carmen

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/