Dear Inés,
The first eigenvariate is a multivariate measure (think PCA) that is a
function of all of the data so differences have to be expected depending
on how many subjects you have in your model.
You can display the difference between the mean and the first
eigenvariate with the following code:
load VOI_XXX.mat
figure,plot(xY.u),hold on,plot(mean(xY.y,2),'r')
Best regards,
Guillaume.
On 26/02/2020 13:22, Ines Del Cerro wrote:
> Dear experts,
>
> I find the same problem as Matthew had long time ago. Depending on the subjects included in the model, the eigenvariate values change. I read the answer to this issue, but I don't really understand why the eigenvariate depend on the model.
>
> I would be very grateful if someone could help me.
>
> Best,
>
> Inés
>
--
Guillaume Flandin, PhD
Wellcome Centre for Human Neuroimaging
UCL Queen Square Institute of Neurology
London WC1N 3BG
|