|
I think your best bet is a nonlinear mixed model, either glimmix or
nlmixed, due to the multiple ED visits for some patients.
Paul R. Swank, Ph.D.
Professor, Developmental Pediatrics
Director of Research, Center for Improving the Readiness of Children for
Learning and Education (C.I.R.C.L.E.)
Medical School
UT Health Science Center at Houston
-----Original Message-----
From: SAS(r) Discussion [mailto:SAS-L@LISTSERV.UGA.EDU] On Behalf Of
baogong jiang
Sent: Wednesday, April 12, 2006 10:11 AM
To: SAS-L@LISTSERV.UGA.EDU
Subject: model building in Logistic regression
Hello:
I am trying to investigate the relationship between the drug compliance
and ED visit.
what I have now:
1. demographic informaiton on patients level (recip_id, age, sex ,race,
and drug compliance) 2. claims records for ED visit (recip_id, er_visit
(0/1) note: some patients have multiple ED visit;
My question:
Can I aggregated the claims record by patients and then fit a negative
binomial model?
If I do not aggregate claims records, how can I fit a logistic model?
thank you the help,
baogong
|
