Hi Letizia, No -D for this design and contrasts. All the best, Anderson On 20 February 2015 at 09:09, Letizia Casiraghi <[log in to unmask] > wrote: > Thanks for your reply! > > This is my contrast matrix: > > EV1 EV2 EV3 EV4 EV5 EV6 > group1>group2 1 -1 0 0 0 0 > group1>group3 1 0 -1 0 0 0 > group1<group2 -1 1 0 0 0 0 > group1<group3 -1 0 1 0 0 0 > group2>group3 0 1 -1 0 0 0 > group3<group2 0 -1 1 0 0 0 > > EV1 and EV3 are for pathological subjects and EV2 is for control subjects, > while EV4, EV5 and EV6 are respectively for age, sex and mean FA. > What I want to check is the difference between subjects in terms of FA > maps. > > Kind regards. > Letizia >