commons-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Thomas Neidhart (JIRA)" <j...@apache.org>
Subject [jira] [Resolved] (MATH-1240) Kolmogorov-Smirnov 2-sample test returns wrong p-value if input data is identical
Date Sun, 28 Jun 2015 10:00:05 GMT

     [ https://issues.apache.org/jira/browse/MATH-1240?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]

Thomas Neidhart resolved MATH-1240.
-----------------------------------
       Resolution: Fixed
    Fix Version/s: 3.6

Fixed in the following commits:

 * 3.6: a019162481161757555c99f3cbce157cc9b1a41b
 * 4.0: 5cfd99f0dcd0d10689e480f0854e859079f125d0

> Kolmogorov-Smirnov 2-sample test returns wrong p-value if input data is identical
> ---------------------------------------------------------------------------------
>
>                 Key: MATH-1240
>                 URL: https://issues.apache.org/jira/browse/MATH-1240
>             Project: Commons Math
>          Issue Type: Sub-task
>            Reporter: Thomas Neidhart
>             Fix For: 4.0, 3.6
>
>
> Depending on the method used, wrong results are returned:
>  * exact -> correct
>  * monteCarlo -> wrong (returns a very small p-value)
>  * approximate -> wrong (returns 0 instead of 1)
> The problem for the approximate version is due to this code snippet in ksSum
> {code}
>         if (t == 0.0) {
>             return 1.0;
>         }
> {code}
> should rather return 0 in this case, but needs to be verified.
> This problem was hidden (due to wrong statistic calculation) in previous versions of
commons-math or resulted in a TooManyIterationsException (if statistic is 0 as correct in
case of identical values).



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

Mime
View raw message