Hi Claus
In spm_PEB.m try changing the last line of the file (line 371) from
C = inv(C + speye(length(C))*exp(-32));
to
C = inv(C + speye(length(C))*exp(-16));'
see the email by Alexa Morcom dated 2007-7-8
hth,
darren
----------
Darren Gitelman, MD
Department of Neurology
Northwestern University
voice: (312) 908-8614
fax: (312) 908-5073
page: (312) 695-1849
email: [log in to unmask]
----------
> -----Original Message-----
> From: SPM (Statistical Parametric Mapping)
> [mailto:[log in to unmask]] On Behalf Of Claus Lamm
> Sent: Saturday, November 10, 2007 3:06 PM
> To: [log in to unmask]
> Subject: [SPM] PPI Matrix close to singular warning
>
> Dear PPI experts:
>
> This error has been repeatedly reported on the list but I
> have found no fix or comment on it so far:
>
> When runing a PPI analysis I get the warning:
> Warning: Matrix is close to singular or badly scaled.
> Results may be inaccurate. RCOND = 1.352361e-16.
>
> I have seen a similar problem with DCM and a message of Klaas
> that it has been fixed by Karl (pasted below). Does the same
> apply for PPI?
>
> THANKS for your help and I hope somenone from the developers
> has time to look at it.
>
> Claus
>
>
> -----
> this was the msg from K Stephan:
>
> Dear Helmut,
>
> this points to problems with matrix inversion during the
> M-step - we have seen that a few times in the past. Karl has
> very recently updated the parameter estimation scheme
> (spm_nlsi_GN) to overcome this problem. If you use the most
> recent version of this routine, it should no longer occur. I
> am not sure whether this version is in the updates directory
> yet; I will check this with John.
> If the same problem still occurs with the new code, please
> send me your model and we will have a look at it.
>
> All the best,
> Klaas
>
|