[pymvpa] Permutation testing and Nipype

[Bill Broderick]

Hi,

Thanks for the response!

> please see my response to Roni few minutes ago, so just collect up to 50
> permutations per subject and then use GroupClusterThreshold to do
> bootstrapping across subjects' permutation results.

I've read over that thread and I like the idea, but I've got a couple
quick questions.

One, we're doing leave-one-subject-out cross-validation, combining the
four runs each subject has, instead of leave-one-run-out (due to
balance issues). Would this change anything in your recommendations?
I.e., can we still use GroupClusterThreshold the way you recommended
for Roni?

Two, we're doing regression in addition to classification (using
EpsilonSVR); that shouldn't change anything either, right?

Finally, you recommend permuting all labels, not just the training set
ones. It's unclear to me why that works. Don't you need to train with
permuted and test with actual labels to get a null distribution. Or is
it okay because Roni's data has one beta per run (whereas we have one
value per trial that we're regressing to, so it's not)?

Thanks,
Bill