Your design is an independent sample t-test, so it must be fully separable.
You will have 4 EVs:
EV1: Normal EV2: Depressed EV3: Anhedonia_Normal EV4:
Anhedonia_Depressed
E1 and EV2 model the group difference; and EV3 and EV4 model the correlation.
You should demean your covariate separately for each group.
Auer, Tibor M.D. Ph.D.
Biomedizinische NMR Forschungs GmbH
am Max-Planck Institut für Biophysikalische Chemie
Am Fassberg 11
37077 Göttingen
Germany
Phone/Work: +49-(0)551-201-1725
Phone/Home: +49-(0)551-387-0076
Mobile: +49-(0)176-8012-7921
Mail: [log in to unmask]
-----Original Message-----
From: FSL - FMRIB's Software Library [mailto:[log in to unmask]] On Behalf Of
Genevieve Yuen
Sent: Tuesday, August 21, 2012 8:44 PM
To: [log in to unmask]
Subject: [FSL] Demeaning covariates
I'm conducting a tbss analysis of radial diffusivity between two groups
(normal versus depressed) and want to include anhedonia (continuous scale
variable) as a covariate. I am wondering if I should demean the anhedonia EV
separately between groups or not, given that the mean anhedonia score is
markedly different between the two groups, normal versus depressed.
I've read through some of the other threads about demeaning across vs between
groups and still am not quite clear on this topic.
Thanks in advance for any help!
-Genevieve
|