Dear SPM experts,
I’m analyzing an influence of anxiety in patients and controls from PET data. With our current PET data set, we want to finish a 2×2 (groups: patients and controls; condition: anxiety and no-anxiety) ANOVA analysis using the flexible factorial model. However, the lack of anxiety-control group is confusing me. There are only 15 no-anxiety patients, 16 anxiety-patients and 12 no-anxiety controls. The specifications are as followings:
1) first factor: subject (independence: yes, variance: equal; grand mean scaling: yes; ANCOVA:yes)
2) second factor: group (2 levels, independence: yes; variance: unequal)
3) third factor: condition (2 levels, independce: no; variance: equal)
The matrix factor:
15 1 1 1;
15 1 1 1;
15 1 1 1;
15 1 1 1;
15 1 1 1;
15 1 1 1;
15 1 1 1;
15 1 1 1;
15 1 1 1;
15 1 1 1;
15 1 1 1;
15 1 1 1;
15 1 1 1;
15 1 1 1;
15 1 1 1;
16 1 2 1;
16 1 2 1;
16 1 2 1;
16 1 2 1;
16 1 2 1;
16 1 2 1;
16 1 2 1;
16 1 2 1;
16 1 2 1;
16 1 2 1;
16 1 2 1;
16 1 2 1;
16 1 2 1;
16 1 2 1;
16 1 2 1;
16 1 2 1;
12 2 1 1;
12 2 1 1;
12 2 1 1;
12 2 1 1;
12 2 1 1;
12 2 1 1;
12 2 1 1;
12 2 1 1;
12 2 1 1;
12 2 1 1;
12 2 1 1;
12 2 1 1
Main effect: factor number: 2
Main effect: factor number: 3
Interaction [2 3]
My questions:
(1) Whether or not the specifications are right?
(2) Can we know the main effect of group, the main effect of condition and group×condition interaction from the current data set (a lack of anxiety controls)?
(3) If the specifications are right, after estimating SPM.mat, how I can set the contrast weight vectors for main effect of group, main effect of condition and interaction (the interface always shows ‘invalid contrast’ and only allow the input of 7 parameters).
Best wishes,
Nanil
|