[pymvpa] GPR woes

[Yaroslav Halchenko]

> Those are not the actual means of the data, it's the means across
> labels.
d'oh -- you are right... things mixed up in my mind ;)

> In fact, I don't understand what any of the summary is
> telling us other than the distribution of labels across the chunks.
> Wouldn't you want to know the mean and standard deviation of the
> actual data per chunk?
yeah -- we should get that in addition to stats on labels/chunks --
stats on data per each label/chunk

> From what I can tell, the only thing that
> tells something similar is the first part of the summary:
> stats: mean=-4.0314e-06 std=0.916641 var=0.84023 min=-1.23648 max=43.8952

yeah -- that is why it is the first one reported ;)

-- 
Yaroslav Halchenko
Research Assistant, Psychology Department, Rutgers-Newark
Student  Ph.D. @ CS Dept. NJIT
Office: (973) 353-1412 | FWD: 82823 | Fax: (973) 353-1171
        101 Warren Str, Smith Hall, Rm 4-105, Newark NJ 07102
WWW:     http://www.linkedin.com/in/yarik