[pymvpa] ROC

[Per B. Sederberg]

Very interesting!  I'm awake for about 10 more minutes, but I'll take
a quick look.

OK, I took a look.  I don't think they should be the same.  An ROC
assumes that if you shift your criterion all the way to one side you
get 0 false and true positives and to the other side you always get
true and false positives.  In other words, you have to pad the points.
 Also, depending on the number of points you have in the middle, your
estimate should will change.  Perhaps this has something to my use of
the trapz function.

Also, we should make that function better anyway.  Right now it
doesn't really handle the labels well, it just does that simple test
of whether it's greater than zero.

P

On Wed, Oct 1, 2008 at 10:58 PM, Yaroslav Halchenko
<debian at onerussian.com> wrote:
>
> I committed and pushed some not-finished yet code... so you could
> torture if you like, but first I want to bring your attention to the
> following misfunction imho:
>
>
> In [27]:AUCErrorFx()([0.5, 0.5], [0, 1])
> Out[27]:1.0
>
> In [28]:AUCErrorFx()([0.5, 0.5, 0.5, 0.5], [0, 1, 0, 1])
> Out[28]:0.75
>
> In [29]:AUCErrorFx()([0.5, 0.5, 0.5, 0.5, 0.5, 0.5], [0, 1, 0, 1, 0, 1])
> Out[29]:0.666666666667
>
> shouldn't in all of those cases we get 0.5?
>
> I know that it is a boundary and artificial case, but!
> So whoever is awake, he is welcome to join the coding ;)
> --
> Yaroslav Halchenko
> Research Assistant, Psychology Department, Rutgers-Newark
> Student  Ph.D. @ CS Dept. NJIT
> Office: (973) 353-5440x263 | FWD: 82823 | Fax: (973) 353-1171
>        101 Warren Str, Smith Hall, Rm 4-105, Newark NJ 07102
> WWW:     http://www.linkedin.com/in/yarik
>
> _______________________________________________
> Pkg-ExpPsy-PyMVPA mailing list
> Pkg-ExpPsy-PyMVPA at lists.alioth.debian.org
> http://lists.alioth.debian.org/mailman/listinfo/pkg-exppsy-pymvpa
>