Dear FSL experts:
I think I have a problem with TBSS. Now, I have two groups. One is patients,the other is healthy controls. I find
age wassignificantly different between the groups, and, accordingly, age was included as a covariate of no interest in
all analyses. And I want to perform High-level two groups,unpaired test.
My design matrix is as follows:
Group EV1(Group A) EV2(Group B) EV3(Age)
My contrasts are GroupA>GroupB, 1 -1 0; GroupA<GroupB,-1 1 0.
Is this correct? But a warning occurred:Problem with processing the model:Warning-design matrix uses different groups
(for different variances),but these do not contain 'separable' EVs for the different groups(it is necessary that,for each
EV,only one of the groups has non-zero values)
Why?
my kind regards,
Lipton
|