Hi, Change the "group" column to all 1's and it will be fine. Cheers, Jeanette On Fri, May 31, 2013 at 4:07 AM, Alena S. <[log in to unmask]> wrote: > Hi, > I am relatively new in FSL,and I have a question about creating design > matrix in Glm. > I want to analyse DTI data from 103 subject, 49 controls and 53 patients > so i ran unpaired T-test and now i want to add additional covariate--age, > so I add age as third EV, so matrix looks like this > > group EV1 EV2 EV3 > 1 1 0 39.2 > 1 1 0 30.6 > 2 0 1 29.5 > 2 0 1 25.5 > > but when i tried to save it, message, which said "problem with processing > the model...warning - design matrix uses different groups (for different > variances) but these do not contain separable EVs for different groups ( it > is necessary that for each EV, only one groups has non-zero values) ", > occurred. > I am not sure what i did wrong. Would you be so nice and help me to figure > out where the problem is. > best regards > Alena >