=========================================================================
Date:         Mon, 24 Jul 2006 16:49:30 -0400
Reply-To:     Gene Maguin <emaguin@buffalo.edu>
Sender:       "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From:         Gene Maguin <emaguin@buffalo.edu>
Subject:      Multivariate ancova using Mixed
In-Reply-To:  <20060724193026.21488.qmail@web38203.mail.mud.yahoo.com>
Content-Type: text/plain; charset="us-ascii"

All,

I'd like to do a multivariate ancova wherein a set of DVs are adjusted for
only THEIR pretest value (and not all covariates). I've posted this before
and the reply from the list as well as somebody at spss was that it wouldn't
work in either glm or manova.

It seems like the setup would be something like

Mixed dv1 dv2 dv3 by group with pre1 pre2 pre3/fixed=group/
   random=intercept.

However, does this sort of model have one intercept or three. I'd think
three because each regression as its own intercept and there is no apriori
reason to expect that all equations will have the same intercept.

Has anyone done anything like this? Can you offer some guidance?