I'm going to run some analyses and have some doubts with respect to the general approach that I should follow. We want to evaluate differences in cortical thickness in three different groups. Shoud I perform an ANOVA (to know if there is a group effect) followed by pairwise comparisons (to localize the difference)? If so, what should I do if results from the ANOVA and pairwise comparisons are localized in different regions? Shoud I restrict the pairwise contrasts to regions where ANOVA revealed significant differences?
Many thanks in advance. Best Regards Gabriel
Yes, restrict the pair-wise comparisons to areas where the ANOVA is significant.
doug
Gabriel Go.Es. wrote:
I'm going to run some analyses and have some doubts with respect to the general approach that I should follow. We want to evaluate differences in cortical thickness in three different groups. Shoud I perform an ANOVA (to know if there is a group effect) followed by pairwise comparisons (to localize the difference)? If so, what should I do if results from the ANOVA and pairwise comparisons are localized in different regions? Shoud I restrict the pairwise contrasts to regions where ANOVA revealed significant differences?
Many thanks in advance.
Best Regards
Gabriel
Freesurfer mailing list Freesurfer@nmr.mgh.harvard.edu https://mail.nmr.mgh.harvard.edu/mailman/listinfo/freesurfer
Thanks Doug
One more, Do I have to perform the pair-wise comparisons onto all significant areas all together?, or can I make it on each one separately?.
Best Gabriel
Date: Mon, 13 Sep 2010 10:24:31 -0400 From: greve@nmr.mgh.harvard.edu To: gabriellbk@hotmail.com CC: freesurfer@nmr.mgh.harvard.edu Subject: Re: [Freesurfer] groups stats doubts
Yes, restrict the pair-wise comparisons to areas where the ANOVA is significant.
doug
Gabriel Go.Es. wrote:
I'm going to run some analyses and have some doubts with respect to the general approach that I should follow. We want to evaluate differences in cortical thickness in three different groups. Shoud I perform an ANOVA (to know if there is a group effect) followed by pairwise comparisons (to localize the difference)? If so, what should I do if results from the ANOVA and pairwise comparisons are localized in different regions? Shoud I restrict the pairwise contrasts to regions where ANOVA revealed significant differences?
Many thanks in advance.
Best Regards
Gabriel
Freesurfer mailing list Freesurfer@nmr.mgh.harvard.edu https://mail.nmr.mgh.harvard.edu/mailman/listinfo/freesurfer
-- Douglas N. Greve, Ph.D. MGH-NMR Center greve@nmr.mgh.harvard.edu Phone Number: 617-724-2358 Fax: 617-726-7422
Bugs: surfer.nmr.mgh.harvard.edu/fswiki/BugReporting FileDrop: www.nmr.mgh.harvard.edu/facility/filedrop/index.html
The information in this e-mail is intended only for the person to whom it is addressed. If you believe this e-mail was sent to you in error and the e-mail contains patient information, please contact the Partners Compliance HelpLine at http://www.partners.org/complianceline . If the e-mail was sent to you in error but does not contain patient information, please contact the sender and properly dispose of the e-mail.
I'm not sure what you mean. Can you elaborate?
doug
Gabriel Go.Es. wrote:
Thanks Doug
One more, Do I have to perform the pair-wise comparisons onto all significant areas all together?, or can I make it on each one separately?.
Best
Gabriel
Date: Mon, 13 Sep 2010 10:24:31 -0400 From: greve@nmr.mgh.harvard.edu To: gabriellbk@hotmail.com CC: freesurfer@nmr.mgh.harvard.edu Subject: Re: [Freesurfer] groups stats doubts
Yes, restrict the pair-wise comparisons to areas where the ANOVA is significant.
doug
Gabriel Go.Es. wrote:
I'm going to run some analyses and have some doubts with respect to the general approach that I should follow. We want to evaluate differences in cortical thickness in three different groups. Shoud I perform an ANOVA (to know if there is a group effect) followed by pairwise comparisons (to localize the difference)? If so, what should I do if results from the ANOVA and pairwise comparisons are localized in different regions? Shoud I restrict the pairwise contrasts to regions where ANOVA revealed significant differences?
Many thanks in advance.
Best Regards
Gabriel
Freesurfer mailing list Freesurfer@nmr.mgh.harvard.edu https://mail.nmr.mgh.harvard.edu/mailman/listinfo/freesurfer
-- Douglas N. Greve, Ph.D. MGH-NMR Center greve@nmr.mgh.harvard.edu Phone Number: 617-724-2358 Fax: 617-726-7422
Bugs: surfer.nmr.mgh.harvard.edu/fswiki/BugReporting FileDrop: www.nmr.mgh.harvard.edu/facility/filedrop/index.html
The information in this e-mail is intended only for the person to
whom it is
addressed. If you believe this e-mail was sent to you in error and
the e-mail
contains patient information, please contact the Partners Compliance
HelpLine at
http://www.partners.org/complianceline . If the e-mail was sent to
you in error
but does not contain patient information, please contact the sender
and properly
dispose of the e-mail.
Thank you for you help Doug, of course I can explain it better
Let's suppose that resulting from the ANOVA I get three significative areas (i.e. enthorhinal, parietal and frontal), do i have to make the pair-wise comparisons on the three areas at once?, or can I perform a pair-wise for enthorhinal, a pair-wise for parietal and a third pair-wise analysis for frontal area?
Gabriel
what do you mean by making the pair-wise all at once? You'll have to correct for multiple comparisons some how. If these are clusters, then it is probably better to correct on a cluster by cluster basis, then do a final correction over the three p-values you get.
doug
Gabriel Go.Es. wrote:
Thank you for you help Doug, of course I can explain it better Let's suppose that resulting from the ANOVA I get three significative areas (i.e. enthorhinal, parietal and frontal), do i have to make the pair-wise comparisons on the three areas at once?, or can I perform a pair-wise for enthorhinal, a pair-wise for parietal and a third pair-wise analysis for frontal area?
Gabriel
Hello
I'm wondering about how to create a label from a cluster wich is significant from a group comparison, I mean, I have made group somparisons and i get some significant clusters, and I want to susbtract that significative cluster and transform it to a label file.
Best Regards
Gabriel
click on it in tksurfer and use the custom fill to fill up to and including the functional threshold, then save the resulting label.
cheers Bruce On Wed, 15 Sep 2010, Gabriel Go.Es. wrote:
Hello
I'm wondering about how to create a label from a cluster wich is significant from a group comparison, I mean, I have made group somparisons and i get some significant clusters, and I want to susbtract that significative cluster and transform it to a label file.
Best Regards
Gabriel
You can also use mri_surfcluster if you want to do it from the command line.
doug
On 9/15/10 8:54 AM, Bruce Fischl wrote:
click on it in tksurfer and use the custom fill to fill up to and including the functional threshold, then save the resulting label.
cheers Bruce On Wed, 15 Sep 2010, Gabriel Go.Es. wrote:
Hello
I'm wondering about how to create a label from a cluster wich is significant from a group comparison, I mean, I have made group somparisons and i get some significant clusters, and I want to susbtract that significative cluster and transform it to a label file.
Best Regards
Gabriel
freesurfer@nmr.mgh.harvard.edu
-
Bruce Fischl -
Douglas Greve -
Douglas N Greve
-
Gabriel Go.Es.