------------- Begin Forwarded Message -------------
From: Roger Staff <[log in to unmask]>
To: [log in to unmask]
cc: [log in to unmask]
Subject: Error!Multi subject covariate only
Date: Fri, 28 Jul 2000 14:08:00 -0400 (EDT)
X-Authentication: IMSP
MIME-Version: 1.0
Dear All
I have 50 SPECT studies (1 scan per patient) with a
range of recorded predictor variables I wish to test
for correlation. I am choosing 'Multi-subject
covariates only' to test for this.
Using spm99 Matlab 5.3.0
After selecting the studies I get:
??? Error while evaluating uicontrol callback
>>>??? Error using spm_spm_ui
unestimable block effect
Looking at the code it appears that the rank of
the design matrix is equal to nscan?
What am I doing wrong?
I can get a result I am sort of expecting using a
similar approach using spm96. I have seen the comment
about changing to CDE and using US language and that
have no effect
yours
Roger Staff
[log in to unmask]
------------- End Forwarded Message -------------
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|