Dear all,
I recently started working with Stata9 and while using svy: regress I
noticed it runned slower than it's counterpart (svyregress) in Stata8.
Also the decimals reported in the standard errors differ slightly
across versions.
I just tried a few svy runs. Didn't notice any differences in the standard
errors (trivial differences wouldn't really bother me anyway) but the speed
difference in the problem I ran was about 3:1 in favor of version 8.2. I
don't know why; perhaps in making the svy commands more general and
powerful they got slowed down a bit. You might try svy-setting them in
version 9 to see if that helps any. Otherwise, if speed is of the essence,
version control may be the way to go for now.
