Ties and the kolmogorov-smirnoff test

[Toke Reichstein]

Hello

Octave provide the service of testing whether or not two data arrays are
drawn from the same distribution. The program applies the
kolmogorov-smiornov_test_2 function when we are interested in comparing
two empirical data arrays. When using it I get the follwoing error:

warning: cannot compute correct p-values with ties
warning: in
/usr/share/octave/2.1.36/m/statistics/tests/kolmogorov_smirnov_test_2.m
near line 79, c

>>> ## There are some ties, so keep only those changes.
>>> warning ("cannot compute correct p-val
  pval: 0.746384
ans = 0.74638

This of cause refer to the fact that some of my observations have the same
values at a specific observation number (ties).

My questions are then:
1. How serious is this problem (probably depend on the number of ties)?
2. Is there a way to easily get around this problem in Octave (without
loosing to many observations)?

Toke



-------------------------------------------------------------
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
-------------------------------------------------------------