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
|
Gang Chen
November 06, 2008 09:57AM
Vinny,

The contrast you obtained with 3dANOVA2 is essentially a one-sample t test on Group B (which means you can run the same test with 3dttest), and that is why the DF is 12. However, the same contrast in GroupAna is done based on both groups with pooled variance. In other words, the variability is estimated with all 31 subjects, even for such a contrast focusing only on one group, leading to the DF being 29. That was also adopted in 3dANOVA2/3 before the modifications a couple of years ago. The new approach in 3dANOVA2/3 is slightly more preferable in case the groups have difference variances, but such a modification is a little difficult to implement in GroupAna. Plus we have 3dLME which can handle such a situation now.

Gang
Reply Quote
RSS
Subject Author Posted

GroupAna.m Problem: Improper calculation of DF for within-subject contrasts?

Vincent Costa November 05, 2008 02:15PM

Not really a problem

Gang Chen November 06, 2008 09:57AM

Re: Not really a problem

Vincent Costa November 06, 2008 10:01AM