I would say that uncorrected results are almost without exception
unacceptable. Yes, there are many different ways in which FMRI stats
can be corrected for multiple comparisons and there can be
disagreement about which is more appropriate in a given situation. But
*any* formal correction is better than none. Without a formal
correction, the reader/reviewer/editor has absolutely *no* idea what
the actual FWE is likely to be. I cannot see how that can be
acceptable in any field of science.
I'm not even saying that everything needs to be p<0.05 corrected -
there's nothing sacred about 0.05 and if a result is extremely novel
or comes from a very hard to study sample, then higher p's might be
warranted. But we need to know what they are, and without formal
correction of some sort, we do not.
On Mon, Jun 4, 2012 at 4:59 PM, Marko Wilke
<[log in to unmask]> wrote:
> Daniel,
>
> this is one of the most complex and hotly debated issues in neuroimaging,
> and there is no easy answer. It depends on your data, group size,
> hypotheses, statistical design, personal preference... if you search the
> archives for, say, Gaussian random field, false discovery rate, small volume
> correction, or cluster size threshold, you will get an idea of how diverse
> the answers can be - about as diverse as the questions. In terms of author
> searches on medline, I would recommend the Nichols and Hayasaka papers, and
> of course the famous Atlantic salmon experiment:
> http://www.mfub.bg.ac.rs/dotAsset/35945.pdf :)
>
> Cheers,
> Marko
>
>
> Daniel Ferreira wrote:
>>
>> Dear all,
>>
>> I have heard that the FWE correction sometimes could be demanding and
>> kill very subtle differences, overall for example in aging studies with
>> normal people and narrow-age intervals, or young people, where changes
>> are supposed to be not very big.
>>
>> So, do you know when uncorrected results are justified or at least
>> permitted instead of FWE? Any paper or information about this specific
>> FWE disadvantages in aid of p<0,001 uncorrected results?
>>
>> Thank you very much in advance
>>
>> Daniel Ferreira
>>
>
> --
> ____________________________________________________
> PD Dr. med. Marko Wilke
> Facharzt für Kinder- und Jugendmedizin
> Leiter, Experimentelle Pädiatrische Neurobildgebung
> Universitäts-Kinderklinik
> Abt. III (Neuropädiatrie)
>
>
> Marko Wilke, MD, PhD
> Pediatrician
> Head, Experimental Pediatric Neuroimaging
> University Children's Hospital
> Dept. III (Pediatric Neurology)
>
>
> Hoppe-Seyler-Str. 1
> D - 72076 Tübingen, Germany
> Tel. +49 7071 29-83416
> Fax +49 7071 29-5473
> [log in to unmask]
>
> http://www.medizin.uni-tuebingen.de/kinder/epn/
> ____________________________________________________
|