[SciPy-Dev] Adding t-test with unequal variances to stats.py

Pauli Virtanen pav@iki...
Sun Jun 3 05:02:27 CDT 2012

03.06.2012 08:13, Junkshops kirjoitti:
> Apparently the thing to do is to beg for your PRs to go into the 
> upcoming version. I'm certainly willing to do so, but I was wondering if 
> the scipy devs respond better to other inveiglements - say, threats of 
> world destruction, under the table 'gifts', favors of a lascivious 
> nature, or cake. All proposals considered.

The only thing needed is someone (= *anyone*, this doesn't have to be a
"scipy developer") with some familiarity in stats to look at it, and
say: "I know this stuff, and looks correct to me." So far, it seems
nobody has found the interest to chip in.

However, having the comparison to R in this case may be enough by itself
to make it clear even to non-experts that things work now as intended.

We nevertheless do have a "blame list" of people who have promised to be
available for scipy.stats on some time scale:

Pauli Virtanen

More information about the SciPy-Dev mailing list