Dear Kasia,
Say you have four columns in your design matrix ordered CM, CF, DM, DF
where C=control, D=disease, M=male and F=female.
The main effect of disease is gotten by the contrast
-1 -1 1 1
(t or F for one versus two-sided).
The main effect of sex is gotten by
-1 1 -1 1
and the interaction by
-1 1 1 -1
Best,
Will.
Kasia wrote:
> Hi,
> In a full factorial design with 2 between subjects factors: like disease (patients vs controls) and sex (females vs males),
> how to define in contrast manager main effects on gray matter volume i.e. effect of disease and effect of sex and interaction of the two?
> Could you please tell me what numbers should I put in the contrast manager to specify the above?
> The manual that I found on the web:
> dbm.neuro.uni-jena.de/vbm8/VBM8-Manual.pdf
> suggest running simply T-tests but how to define interaction?
> Best,
> Kasia
>
>
--
William D. Penny
Wellcome Trust Centre for Neuroimaging
University College London
12 Queen Square
London WC1N 3BG
Tel: 020 7833 7475
FAX: 020 7813 1420
Email: [log in to unmask]
URL: http://www.fil.ion.ucl.ac.uk/~wpenny/
|