Hi - there's no problem in treating these as 3 separate groups with 3 EVs
and 3 variance groups - and the contrast for comparing the combined
patient group would be [ 1 1 -2 ] for example.
Cheers.
On Thu, 9 Sep 2004, Dost Ongur wrote:
> Hello,
> We completed a study where schizophrenia/schizoaffective patients (n=10/10)
> and controls (n=15) carried out a cognitive paradigm. We would normally
> have 2 groups, "patient" and "control" in the design.
> However, we may be interested in asking e.g. whether schizophrenia patients
> show differences from schizoaffectives or controls. Creating 3 groups may
> not be advisable since we have no a priori reason to think that
> schizophrenia and schizoaffective patient groups would have different
> variances associated with them and these would normally be analyzed in a
> single group.
> What would be the best way to approach this issue, maintaining flexibility
> to look at subgroups while also analyzing main groups of patient vs.
> control?
> Thank you,
> Dost
>
Stephen M. Smith DPhil
Associate Director, FMRIB and Analysis Research Coordinator
Oxford University Centre for Functional MRI of the Brain
John Radcliffe Hospital, Headington, Oxford OX3 9DU, UK
+44 (0) 1865 222726 (fax 222717)
[log in to unmask] http://www.fmrib.ox.ac.uk/~steve
|