--- "Bell, Jacqueline S." <[email protected]> wrote:
> Is it valid to use lincom in this situation, with non-zero
> covariance?
Yes, that is not a problem. Non-zero covariances are the rule rather
than the exception, that's why Stata's estimation commands will not
return a vector of standard errors but an entire matrix of the
variances and the covariances in e(V). Commands like -lincom- and
-test- are designed to deal with this.
-- Maarten
BTW. return here means leave behind in memory after you have run an
estimation command. You can see what has been returned by typing
-ereturn list- (or -return list- after non-estimation commands).
-----------------------------------------
Maarten L. Buis
Department of Social Research Methodology
Vrije Universiteit Amsterdam
Boelelaan 1081
1081 HV Amsterdam
The Netherlands
visiting address:
Buitenveldertselaan 3 (Metropolitan), room N515
+31 20 5986715
http://home.fsw.vu.nl/m.buis/
-----------------------------------------
*
* 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/
