Dear all,
I am doing a correlation analysis with a behavioural measure while using some covariates across all my participants (n=54) and I would like to know how the design.con and design.mat should look like in this case.
My first guess was that design.mat should look like this:
/NumWaves 4
/NumPoints 54
/Matrix
41 96 1 0.31
38 99 0 0.33
25 97 0 0.23
17 101 1 1.08 etc
1st column: behavioural measure for correlation; age as covariate; sex as covariate and head motion as covariate.
And the design.con file:
1 0 0 0
-1 0 0 0
1) BUT Do I need a first column with only ones “1” to model the intercept?
/NumWaves 5
/NumPoints 54
/Matrix
1 41 96 1 0.31
1 38 99 0 0.33
1 25 97 0 0.23
1 17 101 1 1.08 etc
And the design.con
0 -1 0 0 0
0 1 0 0 0 ????
2) Also, do I need to add the -D option in randomise in the case of a correlation?
Thanks a lot in advance,
########################################################################
To unsubscribe from the FSL list, click the following link:
https://www.jiscmail.ac.uk/cgi-bin/webadmin?SUBED1=FSL&A=1
|