Gabriel Go.Es. wrote:

Dear Doug,

I would like to be sure that I've understood the rules for the following contrast in a 2x2x2 design with diagnosis (D1, D2), gender (Male, Female) and handedness (Left, Right) as discrete factors.

D1MaleLeft D1MaleRight D1FemaleLeft D1FemaleRight D2MaleLeft D2MaleRight D2FemaleLeft D2FemaleRight

interaction between Diagnosis, Gender, and handedness [ 1 -1 -1 1 -1 1 1 -1]

Correct

interaction between Gender and handedness for D1 [ 1 -1 -1 1 0 0 0 0]/2

Correct

interaction between Gender and handedness for D2 [ 0 0 0 0 -1 1 1 -1]/2

Correct, but I might change the sign to be consistent with that of D1 above

interaction between Diagnosis and handedness for Males [ 1 -1 0 0 -1 1 0 0]/2

Correct

interaction between Diagnosis and handedness for Females [ 0 0 1 -1 0 0 -1 1]/2

Correct

interaction between Diagnosis and Gender for Left [ 1 0 -1 0 -1 0 1 0]/2

Correct

interaction between Diagnosis and Gender for Right [ 0 1 0 -1 0 -1 0 1]/2

Correct

Many thanks in advance.

Gabriel