At 04:17 PM 12/2/2009, Sue wrote:
Thanks for the replies. So there is no option to implement
vce(cluster) only, without the robust option? I looked at section
20.16 in the manual, but didn't see a discussion on this (please
correct me if I'm wrong). Again, I'd appreciate your input.
Robust and cluster go together. Like it says on p. 300 of the manual,
"The robust estimator of variance has one feature that the
conventional estimator does not have: the ability to relax the
assumption of independence of the observations. That is, if you
specify the vce(cluster clustvar) option, it can produce "correct"
standard errors (in the measurement sense), even if the observations
are correlated."
-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
HOME: (574)289-5227
EMAIL: [email protected]
WWW: http://www.nd.edu/~rwilliam
*
* 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/
