On 9 March 2014 10:56, Stephen Smith <[log in to unmask]> wrote:
> Hi Tudor
>
> On 9 Mar 2014, at 10:52, Tudor Popescu <[log in to unmask]> wrote:
>
> Dear FSL experts,
>
> Is the common neuroimaging practice of tightening the significance threshold
> (e.g., p<.001; possibly followed by a similar arbitrary threshold for
> cluster size) in order to avoid correcting for multiple comparisons at all
> correct?
>
>
> No.
>
> Cheers, Steve.
And it's very frustrating that some editors and reviewers are still
allowing such things to be published, when there are any number of
ways of more formally guarding against alpha inflation.
-Tom
--
Centre for Integrative Neuroscience & Neurodynamics
School of Psychology and CLS
University of Reading
Ph. +44 (0)118 378 7530
[log in to unmask]
http://www.personal.reading.ac.uk/~sxs07itj/index.html
|