Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
| From | Volker Ludwig <vludwig@mail.uni-mannheim.de> |
| To | statalist@hsphsun2.harvard.edu |
| Subject | st: df adjustment for robust s.e. with xtreg, fe |
| Date | Sat, 13 Mar 2010 15:15:46 +0100 |
Dear all,does anybody know which df adjustment Stata 11 uses for computing robust standard errors? I thought, it should be NT / (NT-N-K). However, the s.e. turn out to be larger than the ones provided by xtreg ..., fe vce(cluster id).
Obviously, Stata does not make the adjustment for the number of groups. So, my next guess was NT / (NT-K) which gave me "nearly identical" results.(My s.e. are then slightly smaller than Stata's, deviating at the 6th decimal point.)
Precision should not be the problem since I used mata. Does anyone have a better explanation? The manual is silent on this issue as far as I see. Thanks Volker * * 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/