[prev in list] [next in list] [prev in thread] [next in thread] 

List:       sas-l
Subject:    Comparisons of odds ratios
From:       SUBSCRIBE SAS-L Ameribrit <FRP3 () PITT ! EDU>
Date:       2012-06-30 15:01:11
Message-ID: ddaee0f06c5b7117925cf5a82b2a5be3.squirrel () webmail ! pitt ! edu
[Download RAW message or body]

HI Guys: I am running a proc logistic model after stratifying the data by
status of disease as disease X var of interest was significant.

When I look at the wald plot of odds ratios I see that there may be some
diferences. How do I test that the odds ratio for two specific levels of
my categorical variable are diferent? How I need to adjust for multiple
comparisons and get the adjusted odds ratio's and confidence intervals. I
have seen an example of the pairwise comand which does all pairwise
comparisons with the bonferrni adjustment. Is it ok to run this and only
take the pair(s) I am interested in?

thanks Guys

Francis
[prev in list] [next in list] [prev in thread] [next in thread]