Hi all.
In the analysis of a new experiment we got the strange
observation that the estimation of the model fails with
some subjects. The design matrix is the same for all
subject, but estimation of temporal non-spherisity (AR(1))
fails with the following error:
warning: Matrix is close to singular or badly scaled.
Results may be inaccurate.
RCOND= -1.000000e+00.
In spm_reml at 89
In spm_spm at 855
...
Error runing jobs:
Error using => svd
NaN or Inf prevents convergence
What's to do? the easy way is to skip the estimation
of autocorrelation, but that's not realy a good idea
to get valid p-values.
Any other idea?
Michael.
--
<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
Dr. Michael Erb
Sektion f. experimentelle Kernspinresonanz des ZNS
Abteilung Neuroradiologie, Universitaetsklinikum
Hoppe-Seyler_Str. 3, D-72076 Tuebingen
Tel.: +49(0)7071/2987753 priv. +49(0)7071/61559
Fax.: +49(0)7071/294371
e-mail: <[log in to unmask]>
www: http://www.medizin.uni-tuebingen.de/nrad/sektion/
<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
|