Dear John,
An identity matrix over the 3 relevant columns should do it ie. eye(3).
This assumes each effect is described in a single column. If, however, you've used
3 basis functions to model each effect then eye(9) would be appropriate.
Best,
Will.
John D. West wrote:
> Hello.
>
> Could someone explain to me how I would enter an "effects of interest" contrast in SPM5 that would analogous to the automatically generated constrast that exists in SPM2?
>
> I have tried to look into my previous SPM2 analyses and use the contrast listed in the SPM.mat file, but I am getting results that do not look correct. In particular I am trying to generate the above contrast for a 3 group one-way ANOVA.
>
> Any help you can provide would be most appreciated.
>
> Thank you.
> -John West
>
>
--
William D. Penny
Wellcome Department of Imaging Neuroscience
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/
|