Re: st: Strange -robust- results with a singleton dummy (continued)

["Alexander Nervedi" <alexnerdy@hotmail.com>]

Hi !

The emails from Vince, and earlier Mark, have really helped me pinpoint why 
I have been getting such weird F(.,.) for the overall significance of the 
coefficients in my regression (with cluster) estimates.

However, niggling doubt remains when i stare at my regression output - one 
of the estimate has a beta value of of  - 0.12 and SE of 0.06 and so a 
t-stat of - 2.06. I'd expect t-stat values greater than 2 to be signifiant, 
yet the P > |t| is 0.132.  Are these number consistent with each other ?

For the record, I do indeed have a singleton dummy variable at the cluster 
level (instead of a single observation with a 1, i have cluster level 
dummies) and want to control for unobservable cluster level time invariant 
variables.

thanks,

Al,

_________________________________________________________________
Don�t just search. Find. Check out the new MSN Search! 
http://search.msn.click-url.com/go/onm00200636ave/direct/01/

*
*   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/