[pymvpa] normalization: zscore by example?

[J.A. Etzel]

I've also seen (and done!) image- or ROI-wise mean-subtraction or 
scaling before searchlight analysis, but on reflection (and I have some 
simulations, if anyone is interested) I agree with Yaroslav that it's 
not a good idea (for the reason he gives - that it might introduce 
apparent information in uninformative voxels).

The motivation for demeaning I've run into is a worry about detecting 
effects that are not "patterns" in the sense we usually mean, but rather 
uniform differences in BOLD (e.g. all "a" trials have twice the BOLD as 
all "b" trials in the set of voxels). Voxel-wise mean-subtraction does 
not remove this sort of difference, but image-wise mean-subtraction does.

Perhaps, if uniform differences are a concern, we should mean-subtract 
across the voxels within each separate searchlight. This could still 
introduce a bit of blurring (information leakage), but at a smaller 
scale ...

Jo


On 11/7/2011 5:20 PM, Yaroslav Halchenko wrote:
>
> On Mon, 07 Nov 2011, Mike E. Klein wrote:
>>     - My reason for wanting to do this is because of a relative paucity of
>>     examples (9 per run, 3 categories, 9 runs), which I plan to reduce in
>>     number further by some averaging. It seems (to me) that the zscoring would
>>     be more accurate when considering thousands of voxels (per example) as
>>     opposed to several voxels (per run).
>
> oy... full answer and pros/cons/against/for would take a while... there
> are papers which were published and such "preprocessing" was in-place...
> I even debated with one of the authors but never got to submit some kind
> of cririque... in case of Francisco's -- I guess I have missed that
> particular piece or it was in respect only for classification (which is
> as I said is ok)
>
> really coarse reasoning from me:  the problem with zscoring (or
> even just plain demeaning) across voxels is that it leaks information
> among voxels...  e.g. consider the most obvious simplified example
> where you have 2 voxels,  1 of which is informative, and one is not.
>
> after demeaning (let stay to the ground) -- they both become informative
> in respect to the condition of interest, so if you were to judge among
> "who is informative" -- you would be misguided