Hi Jennifer,
I recently asked about Anova models too and also wrote:
"I would suggest a few additions to the 2X2 Anova example of the Feat
manual. These would have been helpful for me:
-description of the first level model (i.e., one contrast testing for the
effect of the treatment on this subject against baseline)
-explanation of the input files (i.e, first level feat dirs with one
contrast, input 1 = subject1 with A0B0, input 3 = subject 3 with A0B1,...)"
Hope that helps.
Cheers,
Teemu
--On torstai 30. marraskuu 2006 21:23 +0000 Jennifer Bramen
<[log in to unmask]> wrote:
> I am trying to undertand how to set up a 2x3 ANOVA, where I can see the
> effect of factor A, effect of factor B, and the interaction between A
> and B.
>
> I am reading the tutorial (slide titled 2-factors 2 - levels. I am having
> difficulty understanding it.
>
> You have 8 inputs, one for each subject. I am guessing this would be a
> 1stlevel.feat directory without repeated measures. These are your EVS
>
> Group EV1 EV2 EV3 EV4
> input 1 1 -1 -1 1 1
> input 2 1 -1 -1 1 1
> input 3 1 -1 1 1 1
> input 4 1 -1 1 -1 1
> input 5 1 1 -1 -1 1
> input 6 1 1 -1 1 1
> input 7 1 1 1 1 1
> input 8 1 1 1 1 1
>
> Where EV1 = Factor A
> EV2 = Factor B
> EV3 = Interaction between A and B
>
> I am definately missing something here. For example, it looks to me like
> you are subtracting subjects 1-4 from subjects 5-8 in EV1...
>
> I think I may be mistaken about what the inputs are, and you don't
> specify.
|