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

st: logistic reg with cluster option


From   Crystal Jarvis <cjarvis@stat.tamu.edu>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: logistic reg with cluster option
Date   Tue, 15 Jul 2003 10:08:25 -0500 (CDT)

I am currently doing logistic regression.
My independent variables are:  Dr. Age, Dr. Race, Dr. Gender, Patient Age,
Patient Race, Patient Gender, length of visit, reason for visit, and
several other variables.

As you can see by running a model with these variables the doctor
variables will be repeated for each patient that doctor has.  i.e the
patients are nested within the doctors.

I have ran the model with STATA using the cluster option and I cluster the
Doctor I.D.
for ex:  logit exercise drage drrace drgender ptage ptrace ptgender lov
rfv, cluster(did)

what makes this statement different from the following

logit exercise drage drrace drgender ptage ptrace ptgender lov rfv, i(did)
pa robust  ?

How also does this effect my interpretation of using the odds ratio for
both methods?

Also, by specifying a cluster it clusters the doctors, but what about the
variables like reason for visit or any patient-related variables, how does
it affect them and their interpretation?

Thanks,
Crystal



*
*   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