I usually generate the expected values for varying levels of
thepredictors, convert the expected values to proportions using a back
tranform, and then plotting these estimated proportions by the values of
the predictors.
Paul R. Swank, Ph.D.
Professor, Developmental Pediatrics
Director of Research,
University of Texas Health Science Center at Houston
-----Original Message-----
From: SPSSX(r) Discussion [mailto:
[hidden email]] On Behalf Of
Nomi
Sent: Thursday, November 16, 2006 1:35 PM
To:
[hidden email]
Subject: logistic regression- interaction graph
Hi,
I've run a logistic regression predicting a binary variable (sick/not
sick) by two categorical variables and the interaction between them. I
now want to create a graph showing the interaction (similar to the
profile plots created by a two way ANOVA). How can I do this?
Thanks!
Nomi