Print

Print


Dear Elsa,

> I am analyzing data in SPM8 and I was wondering whether the FWE corrected p-value involves Bonferroni corrected values or is it based on something else? I have read some very old related posts related to this topic here and I am a bit confused. Is the FWE p value based on random field theory, Bonferroni or does it use both Bonferroni and RFT methods?
> How is the FWE corrected p value calculated in SPM 8?

For voxelwise correction, SPM uses random field theory to calculate a
corrected p value.  This is generally more lenient than the Bonferroni
correction because the topology of the data are taken into account
(the smoothness; i.e. that nearby voxels are not independent).  SPM
also calculates the Bonferroni value and reports the value (random
field theory or Bonferroni-corrected) which is more lenient (which is
usually the random field corrected one).  See spm_P.m.

Hope this helps!

Best regards,
Jonathan

-- 
Dr. Jonathan Peelle
Department of Neurology
University of Pennsylvania
3 West Gates
3400 Spruce Street
Philadelphia, PA 19104
USA
http://jonathanpeelle.net/