Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: probability weights and clogit [Stata 8]


From   "R.E. De Hoyos" <redeho@hotmail.com>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: probability weights and clogit [Stata 8]
Date   Tue, 16 Aug 2005 13:34:29 +0100

Statalist,

I am estimating a -clogit- model using complex survey data. While I would like to have both unbiased and efficient estimators I know that -clogit- is not part of the -svy- commands (at least in Stata 8). To get unbiased estimators though it is sufficient to account for the probability weights or "expansion factors" of the survey, however -clogit- only supports iweights and fweights. I know that aweights can be used as a substitute for pweights and still get the correct point-estimators. Is this also the case for iweghts within a -clogit- context?

On similar grounds, -clogit- includes for the cluster option (in version 8.2), if my survey is the outcome of a multiple-stage design, shall I only include the PSU as the clusters?

Many thanks,

Rafa

PS. I tried sending this email by starting a new thread rather than replying to an old one, but it didn't get through.
________________________
R.E. De Hoyos
Faculty of Economics
University of Cambridge
CB3 9DE, UK
www.econ.cam.ac.uk/phd/red29/ *
* 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/




© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index