Print

---

Dear all,

I have a very basic question about the functioning of Randomise. I was wondering if running the randomise function one sample t-test using 
   
   randomise -i OneSamp4D -o OneSampT -1 -T

       With the data of one group in 'OneSamp4D'

Gives the same result as running a ‘fake’ two-sample t-test
   
   randomise -i TwoSamp4D -o TwoSampT -d design.mat -t design.con -m mask -T 

       With the data of both groups in ‘TwoSamp4D’ 
       design.con = [0 1]
       and design.mat e.g. [0 1; 0 1; 1 0; 0 1; 0 1; ...];

In a (recently developed) toolbox I’m using they implemented the second way, but I wanted to make sure that Randomise performs sign flipping to calculate the clusters, as it would in the first way.

Thanks a lot,

Lars

########################################################################

To unsubscribe from the FSL list, click the following link:
https://www.jiscmail.ac.uk/cgi-bin/webadmin?SUBED1=FSL&A=1