Date:         Fri, 26 Mar 1999 11:53:09 -0500
Reply-To:     Lary Jones <ljones@BINGHAMTON.EDU>
Sender:       "SPSSX(r) Discussion" <SPSSX-L@UGA.CC.UGA.EDU>
From:         Lary Jones <ljones@BINGHAMTON.EDU>
Subject:      Appropriate design: measures of factor
Comments: To: SAS-L@UGA.CC.UGA.EDU
Content-Type: text/plain; charset="us-ascii"

Statis-tickle wizards:
 
A PhD student in psychology came to me today with a question about how to
impliment a design in GLM.  This question is really about choices in the
design, not so much a question of software options.  For purposes of this
question let's say that there are:
 
Between Groups Factors:
        Gender
        Hi-Lo on X
Within Subjects
        5 sessions or trials
 
During each one of the sesions/trials the subjects make a number of
responses.  The dependent measure(s) are the counts of response type A and
response type B.
 
It is unclear to me whether it is better to make this another W/S factor
(response type), or treat these as multivariate "measures" taken at each
trial.  Making this a factor does allow for the direct testing of
interactions with other factors.  Treating this as "measures" means one
would look at the discriminant function of the measures for interpretation.
 
Which way would you go?
 
If I am not makeing the problem clear, please let me know, and I will try
again.
 
TIA,
Lary Jones
_______________________________________________________
Lary Jones          %     Statistical Computing Analyst
Computing Services     %     ..........................
Binghamton University    %        LJones@Binghamton.EDU
Binghamton, NY 13902-6000   %            (607) 777-2879