The design matrix looks strange. It looks like you only have 7
conditions in each group, but you have 14 contrasts in each group. Can
you be more specific about how many conditions you have in each group
and how many contrasts you entered for each subject?
There can be differences between groups as SPM uses the design matrix
to account for unequal variances between groups.
Best Regards, Donald McLaren
=================
D.G. McLaren, Ph.D.
Research Fellow, Department of Neurology, Massachusetts General Hospital and
Harvard Medical School
Postdoctoral Research Fellow, GRECC, Bedford VA
Website: http://www.martinos.org/~mclaren
Office: (773) 406-2464
=====================
This e-mail contains CONFIDENTIAL INFORMATION which may contain PROTECTED
HEALTHCARE INFORMATION and may also be LEGALLY PRIVILEGED and which is
intended only for the use of the individual or entity named above. If the
reader of the e-mail is not the intended recipient or the employee or agent
responsible for delivering it to the intended recipient, you are hereby
notified that you are in possession of confidential and privileged
information. Any unauthorized use, disclosure, copying or the taking of any
action in reliance on the contents of this information is strictly
prohibited and may be unlawful. If you have received this e-mail
unintentionally, please immediately notify the sender via telephone at (773)
406-2464 or email.
On Thu, Dec 20, 2012 at 4:44 AM, Arnold Christiane
<[log in to unmask]> wrote:
> Dear SPM experts,
>
> I am working with multiple group comparisons and therefore I was using the batch for flexible factorial designs in the second level analyses.
> I have two groups of 20 patients each. I acquired 7 conditions per subject.
> Main factor 1 = subjects (independence yes, variance equal)
> Main factor 2 = group (independence yes, variance unequal)
> Main factor 3 = conditions (independence no, variance equal)
> I am interested in the Interaction between group and conditions, thus I choose the interaction term [2 3].
> After estimating, the matrix appears strange. The second group shows much higher x- values than the first one (see picture1).
> I performed a two-sample t-test for the same dataset. The results of brain activation patterns of both analyses for group comparison of the conditions look similar, suggesting that the flexible factorial design is correct.
> Is this phenomenon just a problem of graphic illustration in spm8 or do you have any explanation for that?
> Interestingly performing a different flexible factorial design with completely different contrast images belonging to 6 groups, also the second group shows significant higher x-values in the design matrix compared to all the other groups. Importantly the subjects in the second group are not the same ones than in the other analysis before.
> To search for the problem, I was deleting the second group in my batch and exchanging the sixth group to the second one, now having 5 groups. Then the new second group (being the sixth group in the analysis before) showed these very high x-values, in the design matrix after estimation compared to the subjects in the other groups. How is that possible?
>
>
> Thanks a lot.
>
> Kind regards,
> C. Arnold, University Hospital Frankfurt am Main, Germany
>
>
|