Search All of the Math Forum:
Views expressed in these public forums are not endorsed by
Drexel University or The Math Forum.
|
|
|
|
Re: kolmogov-smirnov, wilcoxon and kruskal tests
Posted:
Dec 23, 2012 5:08 PM
|
|
On Dec 23, 1:31 pm, Rich Ulrich <rich.ulr...@comcast.net> wrote:
> [...] It is conceivable that
> a Monte-carlo test of KS, done by generating 10,000 samples
> with the same margins, would show that the KS test-outcome
> *is* an unusual one. Or it might not.
The exact K-S p-value is 3761029618836*nx!*ny!/(nx+ny)! = .0424,
produced by my translation into Mathematica
of code by Thomas Waterhouse downloaded Oct 3, 2009 from
https://stat.ethz.ch/pipermail/r-devel/2009-July/054106.html
|
|
|
|
