> I have an article that has been reviewed where the only major
complaint
> was that the reviewer would not accept the results as valid because we
> used a FDR correction (p=0.05) -- even though our cluster sizes were
> fairly large, we also used an extent threshold of 25, and our Z-scores
> were generally greater than 5.0. The editor is backing him up, and
> refuses to publish our findings unless we satisfy him that our "result
is
> not a chance finding".
>
> Many of our primary findings would survive a FWE correction if we
applied
> a mask. I find it disturbing, however, that a FDR correction is not
> considered an acceptable method for multiple-comparisons correction by
> this reviewer / editor, and some highly-informative brain / behavior
> correlations in our study require this correction. Any suggestions on
> articles and explanations on the validity of the FDR approach?
Well, my answer is "it depends." Say, if you had a 600-voxel cluster in
the occipital lobe and a 30-voxel cluster in the frontal lobe. Then it
would be easy to claim an activation in the occipital lobe (i.e.,
600-voxel cluster), but it would be very very difficult to make such a
claim for the smaller cluster. This is because, by design, the results
based on an FDR-correction include a certain proportion of false
positives. This means that small clusters, in presence of large
clusters, may be false positives. I agree with you that FDR is a
statistically valid method. But I think you also need to demonstrate
that the cluster you found is too large to be a false positive.
Good luck,
-Satoru
|