Hi - yes, this is fine - though you may get slightly higher zstats on
this contrast if you allow B,C,D to be fit more individually (ie
extend the triple-t-test example) so that more of the variance is
accounted for by the model.
Cheers, Steve.
On 18 Sep 2006, at 22:16, Bradley Goodyear wrote:
> Hi.
> If I have 3 people scanned under 4 conditions (A,B,C,D), and I want
> to see if A is greater than the
> rest (i.e., treating the other conditions as equivalent), would
> this be the correct setup?
>
> EV1 EV2 EV3 EV4
> Subj1 cond A 1 0 0 3
> Subj1 cond B 1 0 0 -1
> Subj1 cond C 1 0 0 -1
> Subj1 cond D 1 0 0 -1
> Subj1 cond A 0 1 0 3
> Subj1 cond B 0 1 0 -1
> Subj1 cond C 0 1 0 -1
> Subj1 cond D 0 1 0 -1
> Subj1 cond A 0 0 1 3
> Subj1 cond B 0 0 1 -1
> Subj1 cond C 0 0 1 -1
> Subj1 cond D 0 0 1 -1
>
> Contrast
> A>b,c,d 0 0 0 1
>
> -BRad
------------------------------------------------------------------------
---
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
------------------------------------------------------------------------
---
|