Date:         Mon, 19 Jul 2004 15:38:05 -0700
Reply-To:     linda <babypenguin13@YAHOO.COM>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         linda <babypenguin13@YAHOO.COM>
Organization: http://groups.google.com
Subject:      Survival analysis- time dependent?
Content-Type: text/plain; charset=ISO-8859-1

Hi,

I am just starting off in using sas for survival analysis work and I
was hoping this group could help me out.  I've been using the proc
phreg command to do an analysis looking at aspirin use as a predictor
of cancer in my dataset.  So far I've been using information on
aspirin use just at baseline entry into the study, however I'd like to
take into account the changes in aspirin use that take place over the
years the study was conducted.  Could anyone provide me with some
advice on how to go about this?  Or is there a way of creating a
variable that takes into account this change over time?  Aspirin use
is just a categorical variable: never, former, and current.  For the
most part, participants start off at never, go to current and then
become former users.  Thanks in advance!
Linda