Show all posts by user
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
Page 2 of 2
Pages: 12
Results 31 - 37 of 37
Hi Gang,
I will just use the path coefficients as inputs for my group analysis.
I do have one question about group comparison of the path coefficients, however. Is there any multiple comparison correction going on? For instance, say I try to attempt to calculate the path coefficients for all possible paths (n=28). When I get the results, some of the connections don't make sense an
by
archerdb
-
AFNI Message Board
Hi Gang,
I have completed the individual analysis, and I am able to do the group analysis with the path coefficients; however, when I try to run the group analysis with both the path coefficients AND t-statistic files, I am getting a singularity issue. The error I am getting is:
Error in solve.default(t(X) %*% W %*% X) :
Lapack routine dgesv: system is exactly singular: U[1,1] = 0
by
archerdb
-
AFNI Message Board
Hello,
I am running 1dSEM analyses to determine path coefficients in a network of 15 ROIs. My goal is to determine the best model in two groups, and compare how the models are different. I have a few questions about this analysis.
1) Do I simply compare the path coefficients between groups? Is there a statistical way to compare coefficients between groups?
2) When computing models,
by
archerdb
-
AFNI Message Board
Hello all!
I am conducting an analysis where I am running ANOVAs and t-tests with control subjects and stroke subjects using 3dMEMA. Now, I have a couple of questions about how I can get the most reliable results. One main issue I am having is that I am getting beta coefficients within the lesions of the stroke participants at the individual level. I want to make sure these betas don't
by
archerdb
-
AFNI Message Board
Hi Gang,
1) One of my factors (A) is within-subject, and the other factor (B) is between-subject. Factor A has 3 (low,medium, high) levels and Factor B has 2 (stroke and control) levels.
2) Yes, I have their t-stats available.
3) I'm trying to see if there is increased activity as the level of Factor A goes from the low to medium to high conditions, and I'm interested if there
by
archerdb
-
AFNI Message Board
Hello-
I am trying to perform a two-factor ANOVA on a stroke dataset, and want to ensure the lesions from each person are not giving me false effects and interactions Thus, I would like to mask out each persons stroke, so that the lesioned voxels for each person are not included in the analysis.
Is this possible to do with 3dANOVA2? If I set the lesioned voxels equal to 0 and used a sub-
by
archerdb
-
AFNI Message Board
Page 2 of 2
Pages: 12