[pymvpa] Sensitivity map with RFE?

[J.A. Etzel]

Your idea might work, though will be non-trivial to interpret. 
Importance-type analyses are very tricky in MVPA, particularly when 
multiple subjects are involved.

You will probably want to include follow-up/validation tests to evaluate 
the regions/features you find most important, sort of like described in 
http://mvpa.blogspot.com/search/label/SA%3APPP .

good luck,
Jo



On 7/19/2013 6:44 AM, marco tettamanti wrote:
> My idea was, since I am doing cross-subject classification, to use RFE
> and obtain a sensitivity map for each fold=1 subject left out, as a
> sensible measure of cross-subject generalization; and then maybe also,
> following the ideas developed in the PyMVPA Manual for feature
> selection, to take the per feature maximum of absolute sensitivities in
> any of the maps or some other representative measures to obtain one map
> I can more easily inspect for spatial anatomical sensitivity.

-- 
Joset A. Etzel, Ph.D.
Research Analyst
Cognitive Control & Psychopathology Lab
Washington University in St. Louis
http://mvpa.blogspot.com/