[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
Re: st: SVY and risk ratio
On 28 Márta 2006, at 16:58, Mwifadhi.Mrisho@stud.unibas.ch wrote:
I have a data set from a household survey and would like to use
in Stata for analysis. I'm trying to find the relationship between
delivery coded as (1=Health Facility 0=Other) and other explanatory
like age of mother, tribe. My interest is obtain risk ratios and
ratios. Can anyone assist me on how to go about it.
You can try your hand at -binreg- which will do robust variance
estimation to take into account clustering in your data, though it
won't accept the -svy- prefix. -binreg- will give risk ratios with
the appropriate option selected.
-binreg-, however, is not guaranteed to find a solution to a
reasonably-specified model, unlike -logistic- which will. I've been
lucky; -binreg- has worked for me most of the time. Others report
less heartening results.
* For searches and help try: