[pymvpa] Accuracy for Each Timepoint in Event-Related Analysis

[Daniel P. Bliss]

I think this question was based on a misinterpretation of what the
event-related analysis actually does.  I was assuming that it conducted a
separate classification analysis for each timepoint, but now I'm inferring
that it conducts a single analysis, treating the timepoints as independent
features.  Is that true?  Is there a way to automate separate analyses for
different timepoints in PyMVPA?

Thanks,
Dan


On Thu, Jan 9, 2014 at 1:32 PM, Daniel P. Bliss <dbliss at berkeley.edu> wrote:

> Hi PyMVPAers,
>
> Part 7 of the tutorial has taught me how to assess the sensitivity of a
> voxel for each timepoint in an event-related analysis, but what I'd really
> like to do is look at the classification accuracy for each timepoint (a
> measure that would incorporate all the voxels).  I can access the overall
> accuracy in that tutorial with
>
> sclf.ca.stats.stats['ACC%']
>
> but I can't find any information about how to get the accuracy for
> individual timepoints (or, for that matter, for individual folds).
>
> I've inspected the keys in sclf.ca.stats.stats, and the contents of
> sclf.ca.stats, but nothing jumps out as being particularly relevant.
>
> Many thanks!
> Dan
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.alioth.debian.org/pipermail/pkg-exppsy-pymvpa/attachments/20140110/2f9c94b5/attachment.html>