Attached is my design.
If anyone has any comments, please feel free to add them!
Regards - Mike
------------------------------------------------
Michael F Glabus, PhD
Associate Professor and Director,
Laboratory of Biological Psychiatry
Department of Psychiatry, School of Medicine
Louisiana State University Health Sciences Center
P.O. Box 33932
1501 Kings Highway
Shreveport, LA, 71130-3932
Tel: 318 675 6050 FAX: 318 675 6148
Cell: 318 518 2644
[log in to unmask]
>-----Original Message-----
>From: SPM (Statistical Parametric Mapping)
>[mailto:[log in to unmask]] On Behalf Of Marc van Ekeren
>Sent: Tuesday, June 20, 2006 2:11 PM
>To: [log in to unmask]
>Subject: Re: [SPM] Three group VBM in SPM5
>
>So you're actually using the 'full factiorial' design, instead
>of the 'flexible factiorial'?
>
>
>----- Original Message -----
>From: Mike Glabus <[log in to unmask]>
>Date: Tuesday, June 20, 2006 8:40 pm
>Subject: Re: [SPM] Three group VBM in SPM5
>
>> Hi folks,
>>
>> Not in the habit of talking to myself, but I have worked out how to
>> do
>> this using the full factorial model :)
>>
>> If anyone's interested, I specified a single factor (group) with
>> three
>> levels, independent, unequal variance, and ANCOVA. I then specified
>> three
>> cells labelled 1, 2, and 3 (for each group) and loaded scans
>> accordingly.
>>
>> I note that my design has a separate regressor for each group for
>> the
>> ANCOVA. If anyone sees any holes in this, please let me know.
>>
>> Regards - Mike
>>
>>
>
|