Dear Giuseppe,
I think you should specify a different design, using the flexible
factorial design option. Specify four factors: subject, A, B, C. Subject
will use settings Independence:Yes, Variance:Equal, while the other
factors will use Independence:No, Variance:Equal. Then enter:
Main effect: 1
Interaction: [2 3 4]
In order to do so, you will have to make the following change:
https://github.com/spm/spm12/blob/master/config/spm_cfg_factorial_design.m#L579
fnums.num = [Inf 1];
Best regards,
Guillaume.
On 14/11/2018 13:03, Giuseppe A. Zito wrote:
> Hello everybody,
>
> I'm trying to implement a 3-way ANOVA with SPM, with the following within-subject factors:
>
> A (2 conditions)
> B (2 conditions)
> C (3 conditions)
>
> Please, see attached file for how my model looks like.
>
> I can run and estimate this model, but when I try to enter the contrasts weights, as suggested by spm_make_contrasts([2 2 3]), I get an error message:
>
> 1 -1 0 1 -1 0 -1 1 0 -1 1 0 <- !invalid contrast
>
> I cannot actually enter any number in the contrast manager.
> Am I doing something wrong? How can I solve this issue?
>
> Thanks a lot for the help,
> Giuseppe
>
--
Guillaume Flandin, PhD
Wellcome Centre for Human Neuroimaging
UCL Queen Square Institute of Neurology
London WC1N 3BG
|