Hi all:
First, thanks to those who replied to my previous thread (multiple response
to binary). I'm not ignoring you, but I haven't closed that thread yet
because now I'm writing a new command to answer my own question, which I'll
send to the list when I'm finished testing it.
Anyway, on a completely separate topic, I have a question about survey
estimation. The svy estimators use a robust variance estimator regardless of
whether the strata, pweight, and psu parameters are specified. So does the
non-survey command -logistic- if you specify weights as pweights.
For this survey that we've done, I've got pweights and I've got strata, but
there was no cluster sampling per se so the PSU parameter is not set.
My question is this:
Given this setup, do I really need to be using the robust variance
estimator? Or should I just use regular non-svy commands.
Thanks,
Lee
Lee Sieswerda, Epidemiologist
Thunder Bay District Health Unit
999 Balmoral Street
Thunder Bay, Ontario
Canada P7B 6E7
Tel: +1 (807) 625-5957
Fax: +1 (807) 623-2369
[email protected]
www.tbdhu.com
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
