Hi,
If you are already modelling the patient group mean effect with an
existing EV then you should probably model the 3 medication groups
with just 2 new EVs, one corresponding to A-B and the other
corresponding to A-C for example. Then you can do an F across simple
contrasts on these to ask where there is any medication effect. See
the first 2 EVs in the following example for more details on
contrasts in this case:
http://www.fmrib.ox.ac.uk/fsl/feat5/
detail.html#TripledTwoGroupDifference
Cheers.
On 22 Jun 2007, at 09:25, Benny Liberg wrote:
> Hi,
>
> I would like to model all medication effects as a covariate on
> second level.
> The patient group has three main groups of medication (A, B, C). I was
> thinking of adding A, B and C as three EV's (orthogonalised wrt to
> patient
> group EV) and do an F-test on all three. Would that be the proper
> way to do
> it? Thanks.
>
> Regards,
> Benny Liberg
------------------------------------------------------------------------
---
Stephen M. Smith, Professor of Biomedical Engineering
Associate Director, Oxford University FMRIB Centre
FMRIB, JR Hospital, Headington, Oxford OX3 9DU, UK
+44 (0) 1865 222726 (fax 222717)
[log in to unmask] http://www.fmrib.ox.ac.uk/~steve
------------------------------------------------------------------------
---
|