Dear Arthur,
> My colleagues and I have submitted a manuscript in which we have used
> the Bonferroni-type correction in SPM96. We cited one of your group's
> manuscripts in which it was stated that this correction "takes into
> account the non-independent nature of the multiple tests." The editors
> of the journal wanted further clarification of the Bonferroni-type
> correction that was used. Would you have a suggestion or reference for
> how to more thoroughly describe the correction done by the program? We
> would greatly appreciate any suggestions you might have.
I would say:
Corrections for the search volume (and implicit multiple comparisons)
were made to the p values using Gaussian field theory. This correction
accomodates spatial correlations inherent in the data and is now
established as the conventional approach to inference in smooth
spatially extended data like images. Details can be found in:
Friston KJ Holmes AP Worsley KJ Poline JB Frith CD and Frackowiak RSJ
Statistical Parametric Maps in functional imaging: A general linear
approach Human Brain Mapping 1995;2;189-210
Friston KJ Worsley KJ Frackowiak RSJ Mazziotta JC & Evans AC Assessing
the significance of focal activations using their spatial extent Human
Brain Mapping 1994;1:214-220
Worsley KJ Marrett S Neelin P Vandal AC Friston KJ Evans AC A unified
statistical approach for determining significant signals in images of
cerebral activation Human Brain Mapping 1996;4:58-73
I hope this helps - Karl
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|