Prev: negative numbers
Next: Summing Rows
From: John on 4 Dec 2009 16:31
I have 2 large scale national surveys looking at malaria prevalence
(binary outcome) which are weighted based on national census cluster
selection. I want to account for clustering effects and also want to
test different predictors of mosquito net ownership and use among
those with/without malaria. Proc genmod with GEEs will not allow for
model fit testing. Is there another model I should try? proc
surveylogistic or proc nlmixed? Which is better and why?
From: tanwan on 4 Dec 2009 23:42
Large scale national surveys with clustering (and perhaps
stratification)? SurveyLogistic wins hands down.

SAS's survey-something procedures were tailor-made for such large
scale survey observational data, like nationally-representative
studies. Surveylogistic allows for model fit testing, using the
methods that are already available with logistic regression, without
loss of generality. SurveyReg, SurveyLogistic, SurveyFreq procs etc
have already been used extensively, for example in the analysis of
NHANES (do a google search) study data or see
http://support.sas.com/documentation/cdl/en/statug/63033/HTML/default/statug_surveylogistic_sect013.htm
for an illustration.
 | 
Pages: 1
Prev: negative numbers
Next: Summing Rows