[pymvpa] A couple of questions from a new MVPA user
raul at lafuentelab.org
Fri Apr 10 15:05:13 UTC 2015
Now I fell more confident about the process I'm following.
I really appreciate it, thank you.
On Wed, Apr 8, 2015 at 5:13 PM, J.A. Etzel <jetzel at wustl.edu> wrote:
> On 4/8/2015 1:37 PM, Raúl Hernández wrote:
>> My questions are,
>> Am I following a correct logic in the analysis?
> From what you wrote, this sounds like a reasonable anatomical ROI-based
> analysis. You'll need to do some sort of multiple-comparisons correction
> for the number of ROIs, of course.
> Is it correct for me to conclude that those areas are involved in
>> processing the categories?
> Well, the regions probably have information related to something having
> to do with the stimulus categories. You always need to be cautious
> interpreting *what* a classifier is actually using for its decision - it
> could be something trivial, like a region that picks up on the
> brightness of the images, rather than the part of the images you were
> interested in.
> good luck,
> Joset A. Etzel, Ph.D.
> Research Analyst
> Cognitive Control & Psychopathology Lab
> Washington University in St. Louis
> Pkg-ExpPsy-PyMVPA mailing list
> Pkg-ExpPsy-PyMVPA at lists.alioth.debian.org
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the Pkg-ExpPsy-PyMVPA