Date:         Wed, 14 Aug 2002 12:05:44 -0600
Reply-To:     Michael Bersick <mbersick@hotmail.com>
Sender:       "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From:         Michael Bersick <mbersick@hotmail.com>
Subject:      repeated measures ANCOVA
Content-Type: text/plain; format=flowed

Hi all,
I have a data set which is a 2x2x3 within subject design, with the 3 level
factor being time. Basically, subjects came in every quarter over the course
of 3 quarters to be tested. In addition, subjects were tested within each
quarter at varying times, and I would like to use the # of days into each
quarter as a covariate to control for differing amounts of experience. The
only thing I have been able to come up with is to regress subjects' data
individually at each quarter and then run a 2x2x3 repeated measures GLM on
the residuals for the 3 quarters, but I have a lingering sense that this is
not quite sound. Is there a better way to do this in GLM?
Thanks for any advice.
MB


_________________________________________________________________
Chat with friends online, try MSN Messenger: http://messenger.msn.com