Hi
I’m looking for a little help with some stats. I’ve gone through the GLM page and forum and I’m still a little bit confused.
I have three separate groups (Control, Trauma, PTSD) and I would like to control for: Age. Alcohol use and IQ. My design matrix for this would like like (covariates are demeaned):
Control Trauma PTSD Age WASI AUDIT
1 0 0 -2.4 0.1. 0.7
1 0 0 0.2 2.4 0.9
0 1 0 1.1 -5.4 -2.2
0 1 0 2.7 -6.9 7.8
0 0 1 4.6 0.1 2.1
0 0 1 -3.7 -4.2 -1.7
My first question is: What should my contrast matrix look like such that I can test the question:
“Is there a difference in FA/MD etc by group when controlling for Age, WASI, and AUDIT, and which individual groups are different? (ie ANOVA with pairwise compairsons).”
In the second part of my analysis I would like to see if the changes I see correlate with PCL and/or symptom severity scores.
My questions here are: Should I add another EV to the matrix above to test the correlation? If so how would I integrate that and test those contrasts?
Sorry for the long question I appreciate any help
Patrick
########################################################################
To unsubscribe from the FSL list, click the following link:
https://www.jiscmail.ac.uk/cgi-bin/webadmin?SUBED1=FSL&A=1
|