Dear Sarah,
<Sarah> <Gregory> wrote:
> Hi Cyril
>
> Thank you so much for your suggestion.
>
> However, I am having a few problems trying to run the MReg analysis
>
> In Scans I have put both data for both groups.
>
> In Covariates I have then added 2 sets of behavioural scores, but it wont let
> me run the analysis giving the following error message
>
> Error running job: Error using ==> spm_meanby
> row dimension mismatch between inputs
>
The number of behavioural scores in set 1 should equal the number in set 2.
And both should equal the total number of scans you have.
OR
you could just enter one set of behavioural scores (with the number of
scores equal to the number of scans) - then when you do the mean-by
thing (covariate interaction and centering ?) SPM will automatically
create two columns in your design matrix.
I'm guessing the latter is appropriate for you.
Best,
Will.
> Sarah
>
>
--
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/
|