Dear Gwen,
If I am interested in group differences and I use age as nuisance effect
(not separate for each group) I think
1,
EV1 EV2 Age
1 0 20
1 0 22
0 1 20
0 1 26
or
2,
EV1 EV2 Age
1 0 -2
1 0 0
0 1 -2
0 1 4
for contrasts
1 -1 0
-1 1 0
gives the same result (randomise without -D). Is it right?
Thank you for your reply.
|