AFNI Message Board

Dear AFNI users-

We are very pleased to announce that the new AFNI Message Board framework is up! Please join us at:

https://discuss.afni.nimh.nih.gov

Existing user accounts have been migrated, so returning users can login by requesting a password reset. New users can create accounts, as well, through a standard account creation process. Please note that these setup emails might initially go to spam folders (esp. for NIH users!), so please check those locations in the beginning.

The current Message Board discussion threads have been migrated to the new framework. The current Message Board will remain visible, but read-only, for a little while.

Sincerely, AFNI HQ

History of AFNI updates  

Previous Message Next Message
Message List New Topic Print View
|
kickan
September 30, 2014 05:21PM
I used 3dClustSim to calculate familywise corrected p-values for clusters, and according to the help text the function by default uses one sided uncorrected voxel-wise p-values to define the clusters. So far so good. However, when I open the AFNI GUI and set the threshold slider to p = 0.01 (which I also used as a voxel-wise threshold for 3dClustSim), the corresponding test value is about 2.70. As I'm looking at results from 3dttest++, I assume that this is a t-vale. When I double checked the threshold in Matlab (using icdf), it seems like 2.70 is the threshold for a TWO-sided test of p = 0.01 (for about 40 degrees of freedom). A one sided test would give a t-value of about 2.4 for p = 0.01.

This made me a bit confused, should I use 2.7 or 2.4 as the voxel-wise threshold?

Is it possible to get one sided p-values in the GUI? I tried checking the box "pos" (for positive) but it did not have any effect on the p-value.
Reply Quote
RSS
Subject Author Posted

One sided p-value threshold in GUI

kickan September 30, 2014 05:21PM

Re: One sided p-value threshold in GUI

gang October 01, 2014 08:05AM