Very simply, the F statistic is too big to show in the space
available.
The F statistic should be
the square of the t statistic, and so around
. di (-372.72)^2
138920.2
You can get more accuracy by rummaging in
saved results.
For most purposes this is good enough, assuming that
you do have 12,318 independent observations with
no dependence structure of any kind!
Nick
n.j.cox@durham.ac.uk
Julia Gamas
> after running a regression I get the following output.
> My question is why is F(1,12317) equal to "." ?
> Since the regression is skipping missing values in the
> data I can't figure out what else is making this
> happen. Any ideas on explaining this will be
> appreciated.
>
>
> Source SS df MS Number of obs = 12318
> F( 1, 12317) = .
> Model 458410.071 1 458410.071 Prob > F = 0.0000
> Residual 40642.8979 12317 3.29974002
> R-squared =
> 0.9186
> Adj R-squared = 0.9186
> Total 499052.969 12318 40.5141232 Root MSE
> = 1.8165
>
>
> t Coef. Std. Err. t P>t [95% Conf.
> Interval]
>
> d -1.442858 .0038711 -372.72 0.000 -1.450446
> -1.43527
>
*
* 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/