Hi,
On 28 Nov 2006, at 14:15, nasser kashou wrote:
> Hello,
>
> I was reading the FEAT manual, specifically paired 2-Group
> difference (2-Sample Paired T-Test) and had a question on it and
> whether the results are what I need.
>
> Ok, so I have 3 subjects and 2 conditions. So, I setup 4 EVs with
> EV1 for the condition. i.e.
> Grp EV1 EV2 EV3 EV4
> 1 1 1 0 0
> 1 1 0 1 0
> 1 1 0 0 1
> 1 -1 1 0 0
> 1 -1 0 1 0
> 1 -1 0 0 1
>
> My question is now in the contrast part. The manual says to setup
> the following
> 1 0 0 0 A-B
> -1 0 0 0 B-A
> I'm assuming this is the average difference of condition A vs B
> across the 3 subjects. You agree?
Yes.
> Now, if I want to look at the difference contrast of condition A vs
> B for each individual subject, would setup 1 or 2 below be correct,
> or neither?
Neither - you can't ask that with this design.
> setup 1:
> 0 1 0 0 A-B subj1
> 0 -1 0 0 B-A subj1
> 0 0 1 0 A-B subj2
> 0 0 -1 0 B-A subj2
> 0 0 0 1 A-B sub3
> 0 0 0 -1 B-A subj3
> or
> setup 2:
> 1 1 0 0 A-B subj1
> -1 1 0 0 B-A subj1
> 1 0 1 0 A-B subj2
> -1 0 1 0 B-A subj2
> 1 0 0 1 A-B sub3
> -1 0 0 1 B-A subj3
>
> Note: I’m using mixed effects. Do I need to use fixed effects if I
> want to do same subject comparison?
That's right, and you would do each subject separately in that case.
Cheers.
>
> I apologize if these questions seem trivial, I believe once I get
> through my stats this will make more sense.
>
> Thanks
>
>
>
> Cheap Talk? Check out Yahoo! Messenger's low PC-to-Phone call rates.
------------------------------------------------------------------------
---
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
------------------------------------------------------------------------
---
|