Switching to the right list...
-
What we need there is a good algorithm for approximating the KS
distribution. I have been corresponding with the author of a very good
one
with a Java implementation but have thus far failed in getting consent to
release under ASL. So at this point, I am looking for an alternative
good
algorithm to implement. All suggestions / unencumbered patches welcome!
See comments on the MATH-431 for other questions.
Just to be sure of what you mean:
Do you want to have a two-sample Kolmogorov-Smirnov test for equality
of distributions in addition to the Mann-Whitney? Or do you need the
Kolmogorov-Smirnov distribution (as stated for example at
http://en.wikipedia.org/wiki/Kolmogorov%E2%80%93Smirnov_test#Kolmogorov_distribution
) in regards to the MATH-428? Sorry, but I'm at bit confused :-).
The goal is to implement the KS test for equality of distributions (or
homogeneity against a reference distribution). To do that we need at least
critical values of the Kolmogorov distribution. The natural way for us to
do that would be to implement the full distribution which would be nice to
have in the distributions package.
Phil
Have you read "Evaluating Kolmogorov’s Distribution" by Marsaglia et
al. available on http://www.jstatsoft.org/v08/i18/paper ? And do you
think their approach would be the way to go?
I am not sure it is best. See the comments here:
http://www.iro.umontreal.ca/~lecuyer/myftp/papers/ksdist.pdf
Phil
Interesting approach for the exact algorithm for Wilcoxon. If we stay
with this, we should ack the original author of the algorithm in the
javadoc. Looks OK to use.
Agree - both on the approach and legal part! Does the author need to
sign anything but write a mail?
Regarding the difference from R, what I usually do in this case is
look
at the R sources to try to explain the difference. Most likely in this
case, what is going on is they are using a different estimation
algorithm
for small n or treating ties differently. The ranking options that we
use
were largely adapted from R, so if that is the problem, it should be
easy to
test. We need to convince ourselves that ours is better or at least a
legitimate alternative. I will take a close look this evening, but it
looks
like the algorithm you are using should be exact. If we can't
reconcile the
difference with R, it would be good to find a way to validate correct
functioning of the algorithm by manufacturing reference data with known
p.
I'll try to investigate the difference, hopefully tomorrow, so that
formal tests can be written and included.
New tests: Wilcoxon signed-rank test and Mann-Whitney U
-------------------------------------------------------
Key: MATH-431
URL: https://issues.apache.org/jira/browse/MATH-431
Project: Commons Math
Issue Type: New Feature
Reporter: Mikkel Meyer Andersen
Assignee: Mikkel Meyer Andersen
Priority: Minor
Attachments: MannWhitneyUTest.java, MannWhitneyUTestImpl.java,
WilcoxonSignedRankTest.java, WilcoxonSignedRankTestImpl.java
Original Estimate: 4h
Remaining Estimate: 4h
Wilcoxon signed-rank test and Mann-Whitney U are commonly used
non-parametric statistical hypothesis tests (e.g. instead of various
t-tests
when normality is not present).
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
---------------------------------------------------------------------
To unsubscribe, e-mail: dev-unsubscr...@commons.apache.org
For additional commands, e-mail: dev-h...@commons.apache.org
