2x2 Fully Between ANOVA
IN.N_subs = [5 5 5 5]; % note the the subjects are entered by condition
IN.Between = [2 2]; % Two factor
IN.BetweenLabs = {{‘Fac1Lev1’ ‘Fac1Lev2’} {‘Fac1Lev1’ ‘Fac1Lev2’}};
IN.Interactions = {[1 2]};
IN.FactorLabs = {‘Factor1’ ‘Factor2’};
IN.EqualVar = [0 0];
IN.Independent = [1 1];
F = CreateDesign(IN);
figure(20); clf
imagesc(F.XX); colormap(gray); shg
I.OutputDir = pwd;
I.F = F;
I.minN = 5;
I.DoOnlyAll = 1;
I.RemoveOutliers=0;
I.Scans = {...
‘s01_c11_c21.nii’;
‘s02_c11_c21.nii’;
‘s03_c11_c21.nii’;
‘s04_c11_c21.nii’;
‘s05_c11_c21.nii’;
‘s06_c11_c22.nii’;
‘s07_c11_c22.nii’;
‘s08_c11_c22.nii’;
‘s09_c11_c22.nii’;
‘s10_c11_c22.nii’;
‘s11_c12_c21.nii’;
‘s12_c12_c21.nii’;
‘s13_c12_c21.nii’;
‘s14_c12_c21.nii’;
‘s15_c12_c21.nii’;
‘s16_c12_c22.nii’;
‘s17_c12_c22.nii’;
‘s18_c12_c22.nii’;
‘s19_c12_c22.nii’;
‘s20_c12_c22.nii’;
};
Below are the standard contrasts for a 2x2 ANOVA. Other contrasts are possible.
I.Cons(1).Groups = {1 2};
I.Cons(1).Levs = [2];
I.Cons(1).ET = 1;
I.Cons(1).mean = 0;
I.Cons(2).Groups = {3 4};
I.Cons(2).Levs = [2];
I.Cons(2).ET = 1;
I.Cons(2).mean = 0;
I.Cons(3).Groups = {5 6 7 8};
I.Cons(3).Levs = [2 2];
I.Cons(3).ET = 1;
I.Cons(3).mean = 0;
I = GLM_Flex(I);
IMPORTANT: Note that the order of scans will go as follows:
Cond1 Lev1 X Cond2 Lev1
Cond1 Lev1 X Cond2 Lev2
Cond1 Lev2 X Cond2 Lev1
Cond1 Lev2 X Cond2 Lev2
Think of this in terms of looping over the factors. If this doesn’t make sense, be sure to look at the design matrix before inputting the scans.