Hi all I am wondering what is the best to present GLM results in a table on top of the visual display. For the significant clusters after clusterwise correction, should we display the Max -log10(p) as in the summary file itself, or the p value directly, or a transformed pvalue like a Z score? Thanks for advices Celine
Hi Celine, you should report the clusterwise p-value (which is neither of those). doug
On 12/17/2013 12:11 PM, Celine Louapre wrote:
Hi all I am wondering what is the best to present GLM results in a table on top of the visual display. For the significant clusters after clusterwise correction, should we display the Max -log10(p) as in the summary file itself, or the p value directly, or a transformed pvalue like a Z score? Thanks for advices Celine
Oh so we don't report the significance itself? because for example if we have a small cluster but highly significant, does the cluster-wise correction p value take it into account? (compared to a large cluster but with lower significance). I may not have completely got this. Thanks Doug Celine
Hi Celine, you should report the clusterwise p-value (which is neither of those). doug
On 12/17/2013 12:11 PM, Celine Louapre wrote:
Hi all I am wondering what is the best to present GLM results in a table on top of the visual display. For the significant clusters after clusterwise correction, should we display the Max -log10(p) as in the summary file itself, or the p value directly, or a transformed pvalue like a Z score? Thanks for advices Celine
-- 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: https://gate.nmr.mgh.harvard.edu/filedrop2 www.nmr.mgh.harvard.edu/facility/filedrop/index.html Outgoing: ftp://surfer.nmr.mgh.harvard.edu/transfer/outgoing/flat/greve/
Freesurfer mailing list Freesurfer@nmr.mgh.harvard.edu https://mail.nmr.mgh.harvard.edu/mailman/listinfo/freesurfer
The cluster p-value is the significance corrected for multiple comparisons. It is possible for a cluster to be large and yet made up of voxels whose individual significances are low. The p-value for such a cluster may be significant, whereas a small cluster made of individual highly significant voxels may not be significant at the cluster level. doug
On 12/17/2013 12:44 PM, Celine Louapre wrote:
Oh so we don't report the significance itself? because for example if we have a small cluster but highly significant, does the cluster-wise correction p value take it into account? (compared to a large cluster but with lower significance). I may not have completely got this. Thanks Doug Celine
Hi Celine, you should report the clusterwise p-value (which is neither of those). doug
On 12/17/2013 12:11 PM, Celine Louapre wrote:
Hi all I am wondering what is the best to present GLM results in a table on top of the visual display. For the significant clusters after clusterwise correction, should we display the Max -log10(p) as in the summary file itself, or the p value directly, or a transformed pvalue like a Z score? Thanks for advices Celine
-- 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: https://gate.nmr.mgh.harvard.edu/filedrop2 www.nmr.mgh.harvard.edu/facility/filedrop/index.html Outgoing: ftp://surfer.nmr.mgh.harvard.edu/transfer/outgoing/flat/greve/
Freesurfer mailing list Freesurfer@nmr.mgh.harvard.edu https://mail.nmr.mgh.harvard.edu/mailman/listinfo/freesurfer
Freesurfer mailing list Freesurfer@nmr.mgh.harvard.edu https://mail.nmr.mgh.harvard.edu/mailman/listinfo/freesurfer
freesurfer@nmr.mgh.harvard.edu
-
Celine Louapre -
Douglas N Greve