Hi,
Correct, all the p-value images generated by randomise are
calculated from the permutation-derived distributions.
Many Regards
Matthew
> So, for the uncorrected TFCE p-values ("tfce_p"), the code retains the
> TFCE test statistic value from every permutation at every voxel, and
> then computes a permutation-based uncorrected p-value at each voxel
> using the test statistic distribution from only that same voxel?
>
> Just wanted to make sure that is the correct understanding.
>
> BTW: In the case of uncorrected "vox_p" values (-x option of
> 'randomise'), are those also computed using the permutation-based
> distribution at each voxel, or are those computed using the
> theoretical
> parametric (t or F) distribution?
>
> thanks,
> -Mike H.
>
>
> On Mon, 2009-11-23 at 09:52 +0000, Matthew Webster wrote:
>> Hi,
>> The uncorrected p-values are purely voxelwise - they are
>> calculated for each voxel using its individual distribution.
>>
>> Many Regards
>>
>> Matthew
>>
>>> Hello FSL experts,
>>> My correspondence with Mark has made be curious about the following:
>>>
>>> How is the uncorrected p-value computed for the TFCE test
>>> statistic of
>>> 'randomise'?
>>>
>>> cheers,
>>> Mike H.
>>>
>>>
>>> --
>>> Michael Harms, Ph.D.
>>> --------------------------------------------------------------------
>>> Conte Center for the Neuroscience of Mental Disorders
>>> Washington University School of Medicine
>>> Department of Psychiatry, Box 8134
>>> Renard Hospital, Room 6615 Tel: 314-747-6173
>>> 660 South Euclid Ave. Fax: 314-747-2182
>>> St. Louis, MO 63110 Email: [log in to unmask]
>>> --------------------------------------------------------------------
>>>
>
|