Hi FSL experts,
I am following up on a question i have asked a while ago regarding the best practice when setting up a PPI design.
I have 2 psychological EV's that i am interested in (say EV1 watching scary clips and EV2 watching funny clips) and a physiological EV (the timeserios from a selected ROI).
When i have asked about how best to set up this design in the past Anderson recommended (if i understood correctly) either doing a 1 sample T for each individual interaction (EV1*EV3 & EV2*EV3) or running a three-way interaction between all the EV's.
Assuming i would like to go for the second option, how would i set up my design? would i set up my 3 EV's and an additional interaction EV (as usually is done in PPI analysis)? but that would yield only one cope for the interaction EV, how would that be interpreted? or should i have an interaction EV for all possible interactions (EV1*EV2 & EV1*EV3 & EV2*EV3 & EV1*EV2*EV3) and run an F test on them all? or should i do something entirely different?
Thank you!
Navot
To unsubscribe from the FSL list, click the following link:
https://www.jiscmail.ac.uk/cgi-bin/webadmin?SUBED1=FSL&A=1
|