[pymvpa] Searchlight map question.
michael.hanke at gmail.com
Fri Sep 7 14:32:14 UTC 2012
Here is the two second answer:
On Sep 7, 2012 4:16 PM, "Roberto Guidotti" <robbenson18 at gmail.com> wrote:
> Hi all,
> a two second question about searchlight map.
> I did a whole brain searchlight analysis with two classes, using a SVM
and cross validation with half partitioner. As results I obtained a map
with accuracies for each voxels and two volumes, this means that I have a
volume for each CV fold?
> If yes (with high probability) you'll use as result the intersection of
separated maps or something else?
Whatever you prefer. Most people go with the average.
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the Pkg-ExpPsy-PyMVPA