Re: st: reg with robust, F-stat reported as a dot.

["Joel E. Pike" <jpike@bus.wisc.edu>]

Francisco

See my post from yesterday with the same question.

You can get the same results, I believe, with test using the second syntax, 
which will test the hypothesis that all coefficients are equal to zero and 
give you the F (k, n) and Prob > F results.

Joel

At 03:43 PM 6/29/02 -0300, you wrote:

> Dear Statalisters:
>
> I'm running simple OLS regressions with robust standard errors.
> In some cases the F-stat of the regression and Prob>F are reported as a dot
> ".", like in the example below.
> The problem does not show up if I run the same regression without robust
> standard errors.
> Can someone tell me what can be going on here?
> Thanks,
>                  Francisco.
>
> Regression with robust standard errors                 Number of obs =
> 1175
>                                                        F( 25,  1148) =
> .
>                                                        Prob > F      =
> .
>                                                        R-squared     =
> 0.6376
>                                                        Root MSE      =
> .55503
>
> *
> *   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/
*************************************************
Joel E. Pike
School of Business
University of Wisconsin
1238 Grainger Hall
975 University Avenue
Madison, WI  53706-1323
Tel: 608-265-4830
*************************************************

*
*   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/