Dear Karl,
The following are the study design (SPECT), the analytical design (based on
my previous communications with you) which are followed by my question:
Study Design:
Patients before treatment Scan 1 (PTS1)
Patients after treatment Scan 2 (PTS2)
Patients who will not be treated scan 1(PNTS1)
Patients who are not treated scan 2 (PNTS2)
Heathy subjects who will not be treated scan 1 (HNTS1)
Healthy subjects who are not treated scan 2 (HNTS2)
Gender is taken as covariate of no interest (Nuisacne)
MMSE (Psychological test) is entered as covariate)
Analytical Design:
Multi-group ANCOVA in SPM2 (For now, I don't do it in SPM5b as it is a beta
version). All scaled to 50 for global corrections, as these are SPECT
images.
2 x 2 design
PTS1-------------time--------------> PST2
PNTS1------------time-------------->PNTS2
2 x 2 design
PNTS1------------time-------------->PNTS2
HNTS1----------time--------------->HNTS2
Contrasts for each 2 x 2 design:
0 0 0 0 1 -1 -1 1 (treatment x MMSE x Time interactions)
-1 1 1 -1 0 0 0 0 (treatment interactions in patients with time in the
first 2 x 2 design or subject conditions (disease) interactions with time
in the second 2 x 2 design)
etc.
My question:
I remember that I read somewhere in the mail base that in such situations
we should do two 2 x 2 analyses instead of one 3 x 2. Am I correct? If so
why?
Kindest regards,
Shary
Shary
Shahryar Rafi-Tari, M.Sc.
Database Consultant / Imaging Analyst
2075 Bayview Avenue
Sunnybrook & Women's College Health Sciences Centre
Linda C Campbell Cognitive Neurology Research Unit
Room B630
Toronto, Ontario, Canada M4N 3M5
E-mails: [log in to unmask]
Disclaimer: This e-mail is intended for the addressee(s) only, and may also
be confidential. Any review, retransmission, or other use of this
information by persons other than the addressee is strictly prohibited. If
you are not the addressee or received this by mistake, please contact the
sender and delete the material from all your computers.
|