[pymvpa] information prevalence inference

[Yaroslav Halchenko]

On Tue, 20 Jun 2017, Wolfgang Pauli wrote:

> Hi!

> Is there an implementation of the prevalence inference method, as
> proposed by Allefeld et al (2016), included in pymvpa (e.g. version
> 2.5)? I am considering doing this, unless it is already ready to go.

I don't think anyone got to it so far... when preprint got out I just
experimented to replicate those demonstrated effects and see if with AUC
we are experiencing the same: FWIW here is some old notebook
http://nbviewer.jupyter.org/url/www.onerussian.com/tmp/test_ttest.ipynb

I guess implementation for prevalence testing should be relatively
straightforward, especially since IIRC there is matlab code already
online https://github.com/allefeld/prevalence-permutation/releases

-- 
Yaroslav O. Halchenko
Center for Open Neuroscience     http://centerforopenneuroscience.org
Dartmouth College, 419 Moore Hall, Hinman Box 6207, Hanover, NH 03755
Phone: +1 (603) 646-9834                       Fax: +1 (603) 646-1419
WWW:   http://www.linkedin.com/in/yarik