[pymvpa] Biased estimates by leave-one-out cross-validations in?PyMVPA 2

Yaroslav Halchenko debian at onerussian.com
Sat Apr 21 00:17:53 UTC 2012

Ping-Hui Chiu <chiupinghui at gmail.com> wrote:
> ds=fsel(ds)
> ds_chunks=cv_chunks(ds)

Because you double dip here: feature selection should be trained only on training portion of the data
Use FeatureSelectionClassifier
I would also recommend to go through or tutorial which highlights such cases

Sent from a phone which beats iPhone.

More information about the Pkg-ExpPsy-PyMVPA mailing list