[pymvpa] Pattern localization

[Matthias Ekman]

>>> so -- either those raw (mean) sensitivities, or their stability assessment
>>> across splits (just make sure that you normalized your features prior doing
>>> that, with zscore or smth else).  If there is no feature selection, than,
>>> permutation testing F- or converted z-scores might be also a nice one.
>>> In both cases though you need to decide on the thresholding scheme ;)
>> I looked through some papers and it seems to me, that this point is  
>> somehow arbitrary. Some guys are taking the "best" 20% features, some  
>> others discard those features with SD > 2, others show those features  
>> which have an overlap with other subjects features... those were noise  
>> perturbation shows an min. effect of 30% ... and so on.
> 
> yeah... there is also yet another way, which is related to
> null-hypothesis, permutation testing, false discovery rate... it is not published
> anywhere and we had not a chance/time to elaborate on it, but you might
> look into
> mvpa/misc/transformers.py : DistPValue

Cool! Thanks again for the hint.

from the source code:
"WARNING: Highly experimental/slow/etc: no theoretical grounds have been 
presented in any paper, nor proven"

Sounds like: If you use it (right now), you must be total idiot ;-)

But, would be very nice to have some p-values and map it with a 
threshold using a multiple comparison correction criterion. I'm really 
looking forward to this transformation.

>> In your paper (Hanson & Halchenko, 2008) you used a recursive feature  
>> elimination algorithm to sequentially eliminated features with the  
>> smallest squared values of the separating plane normal coefficients.  
>> Then you derived weights for the FACE class by using only FACE class SVs  
>> (and for the HOUSE class in the same way).
> correct... important to mention that in preprocessing data was standardized
> (zscored) against baseline condition. Otherwise, taking per class means
> would have little to no sense

OK! I assume with "baseline condition" you mean the explicit baseline 
("rest") and not the implicit baseline which would be everything else, 
except FACE and HOUSE (like e.g. FSL does), right?

>> Is there also some supplemental (may be I forgot about) where it is  
>> shown how to extract only special class SVs? Or would it be possible to  
>> explain this procedure?
> all that analysis was done prior we started massive PyMVPA movement and
> advocation of code as supplementals ;)  I can dig out some of that code
> which was crafted around stand-alone patched lightsvm but I guess it
> would make it easier just to explain and actually patch LinearSVMWeights
> to do this procedure, which is quite simple one:  for each of 2 classes
> SVM assigns weights per each category -- positive for +1, negative for
> -1. So it is just to sum up corresponding SVs accordingly... let me
> simply actually patch libsvm's LinearSVMWeights for now... I will let
> you know whenever it is done

Oh great! Thank you very much for putting so much work into this!

Best Regards,
Matthias