Hi Patricia,
here is what Tom (Nichols) said on this earlier this year:
"The only difference between the two approaches is the assumption of common error variance over the 3rd group if included (possibly bad), and a corresponding increase in DF (always good).
So there's no right answer...
The safe way is to only study the data needed (2nd approach) because if it happens that group C has wildly smaller variance you can get inflated significances (or reduced power if it has wildly larger variance, but still not 'accurate' inferences relative to 'truth').
However, if the 'master' inference is determined by the F-test across all groups, then it's fine to work with the big model - 1st approach - since you're depending on it's validity anyway."
Hope this helps,
Gwenaelle
> De: SUBSCRIBE FSL Patricia Pires <[log in to unmask]>
> Objet: [FSL] Glm
> À: [log in to unmask]
> Date: Mardi 16 novembre 2010, 14h27
> Hello!
>
> I would like to know which contrast is more correct if I
> have a healthy control group and 3 subgroups of patients
> using randomise, Glm and its outputs:
>
> 1) Analyze the healthy control group contrasting to each
> depressive group separately (i.e. analize 3 Glm), or
>
> 2) Analiyze all groups together in Glm (with their correct
> contrast)
>
> I have done both analysis and there are different outputs
> in fslview and in cluster command, which is the most
> recommended test?
>
> Thank you,
>
> Pat.
--------------------------------------------------------------------
Gwenaëlle Douaud, PhD
FMRIB Centre, University of Oxford
John Radcliffe Hospital, Headington OX3 9DU Oxford UK
Tel: +44 (0) 1865 222 523 Fax: +44 (0) 1865 222 717
www.fmrib.ox.ac.uk/~douaud
--------------------------------------------------------------------
|