Date:         Fri, 17 May 2002 07:10:15 -0700
Reply-To:     Helena Gross <spygirl658@YAHOO.COM>
Sender:       "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From:         Helena Gross <spygirl658@YAHOO.COM>
Subject:      more help with post-hoc in within-subjects ANOVA
Content-Type: text/plain; charset=us-ascii

I should have provided more information about what I
have so far.  I need to do post-hoc tests (Scheffe and
Tukey) for a within-subjects ANOVA.  There is a
significant difference between at least one of the
three within-subjects factors, but I need to know
which.

G = between-subjects variable with two levels
V1 V2 V3 are three levels of a within-subjects
variable

PROC GLM;
   CLASS G;
   MODEL G=V1 V2 V3;
      REPEATED TIME 3;
RUN;

When I try to use the MEANS statement to do the
post-hoc tests, I get an error saying that only class
variables are allowed in this effect.  What do I need
to do?

Again, any help is greatly appreciated.  Thanks!

__________________________________________________
Do You Yahoo!?
LAUNCH - Your Yahoo! Music Experience
http://launch.yahoo.com