Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down at the end of May, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

re:st: Are standard errors valid when the F-stat is missing?


From   Christopher Baum <kit.baum@bc.edu>
To   "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu>
Subject   re:st: Are standard errors valid when the F-stat is missing?
Date   Wed, 28 Dec 2011 13:58:15 -0500

<>
I´m estimating an OLS regression using the robust option for a main
sample and different subsamples. For the main sample I obtained the F
stat and all the st. errors; however, for the subsamples the F stat is
missing. I have checked and this is due to the fact that for some of
the subsamples there are variables with few non-zero observations.
Even though I could go and check for each subsample which variables
are those and dropped them from the estimation, I was wondering if the
standard errors obtained for each of the variables in the subsample
are valid under the scenario with the F-stat missing for the
estimation.

It would be useful to see the actual output from one of the subsamples. OLS does not care how many 
zero values there are in a regressor as long as not all of them are zero, so 'few non-zero observations'
matters not.

Kit

Kit Baum   |   Boston College Economics and DIW Berlin   |   http://ideas.repec.org/e/pba1.html
An Introduction to Stata Programming   |   http://www.stata-press.com/books/isp.html
An Introduction to Modern Econometrics Using Stata   |   http://www.stata-press.com/books/imeus.html


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


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index