Hi All,
I did a study on language production in 18 subjects, 9 were young (22
- 32 years), 9 were old (60 - 83 years). In addition to a two-group
analysis, I would like to perform a single-group analysis with an
additional covariate (age).
I have defined the EVs as suggested in the FEAT manual ("Single-Group
Average with Additional Covariate"), i.e.
Group EV1 EV2
1 1 -20
1 1 -26
1 1 -16
1 1 -22
1 1 -18
1 1 -25
1 1 -26
1 1 -25
1 1 -22
1 1 26
1 1 34
1 1 20
1 1 14
1 1 24
1 1 16
1 1 12
1 1 17
1 1 35
EV2 is individual age - mean age.
FEAT tells me that this design matrix is rank-deficient. Choosing
"Orthogonalisations" in the "Full model setup" did not solve the
problem.
How can I change the EVs to obtain a working design matrix containing
this covariate?
Your help is very much appreciated!
Peter Soros
|