My experimental design includes 3 discrete factors: diagnosis with two levels (A, B); genotype with two levels (G, T); gender (F, M), and two covariates.

So I can get 8 classes: AGF, AGM, ATF,ATM, BGF, BGM, BTF, BTM.

1)  I want to perform 2 (diagnosis)* 2(genotype) interaction analysis with regressing out the effect of gender and two covariates, but I don't know the rules for setting the contrasts for the interaction.  The contrast matrix I used is:

0.25 0.25 -0.25 -0.25 -0.25 -0.25 0.25 0.25 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0

is it correct?

If it is correct, how to explain the results, for example, what does the positive (or negative) clusters stand for?  Or the clusters showed in the t-test statistical map are the regions that have the significant interaction?

 

 2) When I perform the main effect of dignosis, is the following matrix I used correct?

0.25 0.25 0.25 0.25 -0.25 -0.25 -0.25 -0.25 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0  (I think it regressed out the effect of genotype and gender, that is it takes the genotype as a covariable)

 Or I  should create another fsgd file, that has 4 classes: AF, AM, BF, BM. And I can use the matrix (0.5 0.5 -0.5 -0.5 0 0 0 0 0 0 0 0) to perform the main effect of diagnosis. which one is right?

 

Any help will be very appreciated.

 

Best wishes,

 

Meng Li