wilcoxon_test, large number of points

[luc . lefebvre]

Hi,

I am not sure if this is the appropriate list, if not, I apologize.

I ran the wilcoxon_test.m on two sets of points (n=1022) with Octave
(v2.0.14 on ppc, v2.0.16 on i386) and I get the same "p" value
(p=3.9175e-07).

If I run the same data through Sigmastat I get a radically  different "p"
value of 0.14.

Is there a known problem with the implementation of the wilcoxon test in
octave?  Am I "missing" something?

tia

--
Luc Lefebvre                                 o
                                            /`-'
Open Source, a strategic choice             \
for mission-critical applications        ___/___./

Key fingerprint = D2E5 5E35 B910 6F4E 0242  EC63 0FD9 96D0 C7F4 784E



-------------------------------------------------------------
Octave is freely available under the terms of the GNU GPL.

Octave's home on the web:  http://www.octave.org
How to fund new projects:  http://www.octave.org/funding.html
Subscription information:  http://www.octave.org/archive.html
-------------------------------------------------------------