*Dear Freesurfer Users and Developers, * Could you please help me to clarify the key steps implemented into the Monte Carlo approach for multiple comparisons correction? As far as I understood, it consists of running many permutations for fitting the measurements of different ROI sizes, which are being selected randomly according to predefined p-value. The process stops when optimal cluster is found and as a result we have the clusters of difference with clusterwise p-value and 90% C.I.... Am I wrong? Thank you very much beforehand...
Regards, Alexander Ivanov
Hi Alex, try reading these papers:
ftp://surfer.nmr.mgh.harvard.edu/transfer/outgoing/flat/greve/hayasaka.2003.ni.1014.clustersize.pdf ftp://surfer.nmr.mgh.harvard.edu/transfer/outgoing/flat/greve/hagler.2006.ni.surfcluster.pdf
if you still have questions, feel free to ask. doug
Alexander Ivanov wrote:
*Dear Freesurfer Users and Developers,
Could you please help me to clarify the key steps implemented into the Monte Carlo approach for multiple comparisons correction? As far as I understood, it consists of running many permutations for fitting the measurements of different ROI sizes, which are being selected randomly according to predefined p-value. The process stops when optimal cluster is found and as a result we have the clusters of difference with clusterwise p-value and 90% C.I.... Am I wrong? Thank you very much beforehand...
Regards, Alexander Ivanov
Freesurfer mailing list Freesurfer@nmr.mgh.harvard.edu https://mail.nmr.mgh.harvard.edu/mailman/listinfo/freesurfer
freesurfer@nmr.mgh.harvard.edu
-
Alexander Ivanov -
Douglas N Greve