Dear FSL Experts,
We used PALM to analyze our data (three modalities: VBM-derived GM volume, fractional anisotropy, outputs from FSLnets) with the NPC option.
Our design is regression with clinical variables. We got some significant p-values and also some outputs named as **_npc_fisher_c1.csv
We were wondering whether it is possible to convert the value inside these files (do they represent T statistics?) to r value (correlation coefficient)
We notice that there is way (shown in https://www.jiscmail.ac.uk/cgi-bin/webadmin?A2=ind1701&L=FSL&P=R125162&X=F9ACBBB6DD9716591B&Y=zhangjianeave%40gmail.com) to convert the t-statistics to r:
r = sign(t) * sqrt(t^2/(df+t^2))
Using such formula, we got very high values (e.g., 0.95).
Is it correct to apply such formula or are there other ways to perform it?
Thanks,
Jian
########################################################################
To unsubscribe from the FSL list, click the following link:
https://www.jiscmail.ac.uk/cgi-bin/webadmin?SUBED1=FSL&A=1
|