Date:         Tue, 11 Aug 1998 13:23:59 -0500
Reply-To:     gkeeler@PSYCH.MC.DUKE.EDU
Sender:       "SAS(r) Discussion" <SAS-L@UGA.CC.UGA.EDU>
From:         gkeeler@PSYCH.MC.DUKE.EDU
Organization: Duke University, Durham, NC, USA
Subject:      Re: Weighted Logistic Regression
Content-Type: text/plain; charset=us-ascii

mt_rogel@my-dejanews.com wrote:
 
>  The sampling design used was a two-stage stratified cluster and i would like
> to
> incorporate this when i use logistic regression.  how i can do this.
 
Trisha, PROC LOGISTIC by itself does NOT incorporate the weight variable
correctly. You can check the results of the procedure yourself by running it
with
and without the weight statement. I seem to remember that the calculated
variance
doesn't change when you add the weight statement.
 
There are several ways to get around this error.
 
1) The LOGITSE macro adjusts the variance using the "sandwich" correction
factor.
It is available at the SAS website but I will mail a copy of it directly to
you.
 
2) Use the GLIMMIX macro for logistic regression using the EMPIRICLE option.
This
macro is installed with SAS in the STAT\SAMPLE directory.
 
3) Use PROC GENMOD.
 
Good Luck...........Gordon