Hi,
this sounds much like the problem (hopefully) resolved in
http://www.jiscmail.ac.uk/cgi-bin/webadmin?A2=ind0605&L=spm&O=D&P=10258
Otherwise, you could try the workaround suggested in
http://www.jiscmail.ac.uk/cgi-bin/webadmin?A2=ind0605&L=spm&O=D&P=5671
Good luck!
Andreas
On Fri, 12 May 2006 18:44:42 +0100, john brooks <[log in to unmask]>
wrote:
>hello,
>i'm trying to do something that was very simple in spm2 and perhaps i'm
doing something
>incorrectly in spm5. i have a set of 15 PET scans that consist of
absolute data. i would like to
>correlate them a single measure.
>i have chosen 'multiple regression' and specified the measure as a
covariate. however, when i
>estimate the model, i get what is below.
>i would greatly appreciate any explanation of what it means.
>thanks.
>
>Warning: Matrix is singular to working precision.
>> In spm_reml at 87
> In spm_spm at 860
> In spm_spm at 299
>??? Error using ==> svd
>NaN or Inf prevents convergence.
>
>Error in ==> pinv at 29
> [U,S,V] = svd(A,0);
>
>Error in ==> spm_reml at 92
> Cq = pinv(X'*iCX);
>
>Error in ==> spm_spm at 860
> [V,h] = spm_reml(Cy,xX.X,xVi.Vi);
>
>Error in ==> spm_spm at 299
> spm_spm(SPM);
>
>??? Error while evaluating uicontrol Callback.
>=========================================================================
|