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/
_______________________________________________
Pkg-ExpPsy-PyMVPA mailing list
[email protected]
http://lists.alioth.debian.org/cgi-bin/mailman/listinfo/pkg-exppsy-pymvpa
