commons-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Phil Steitz (JIRA)" <j...@apache.org>
Subject [jira] [Comment Edited] (MATH-1034) Add binomial test
Date Thu, 26 Sep 2013 15:44:03 GMT

    [ https://issues.apache.org/jira/browse/MATH-1034?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13778911#comment-13778911
] 

Phil Steitz edited comment on MATH-1034 at 9/26/13 3:42 PM:
------------------------------------------------------------

Looks good overall.  Thanks!  I will do a more careful review and commit in the next couple
of days.  There are a few things that need to be changed / verified / documented.

1. The exceptions need to be MathExceptions and the strings need to be externalized.  This
is a little arcane and I will just handle it if you don't want to mess with learning how this
works in [math].
2. I don't follow exactly what is going on in the 2-sided test.  I need to brush up on / play
with the math-stat here.  The distribution is *not* symmetric, so it is not crystal clear
to me that what you are doing is correct.  Most likely I am just not looking at the distribution
theory the right way.  In any case, it is probably worth a note and/or reference.  Another
thing that would make me happy (if it works) is to validate the 2-sided test by performing
a (degenerate) Chi-Square test.  Could be what I am missing is that in the setup here these
are not the same.  I will dig into this a little but references are appreciated.
3. I assume the reference values in the tests come from R?  You should make it clear where
they come from.

Thanks again for the patch!

                
      was (Author: psteitz):
    Looks good overall.  Thanks!  I will do a more careful review and commit in the next couple
of days.  There are a few things that need to be changed / verified / documented.

1. The exceptions need to be MathExceptions and the strings need to be externalized.  This
is a little arcane and I will just handle it if you don't want to mess with learning how this
works in [math].
2. We use {@code} instead of <code> now and we are also moving to use embedded LaTeX
via MathJax for formulas / symbols instead of html entities.  Again, I will take care of this.
3. I don't follow exactly what is going on in the 2-sided test.  I need to brush up on / play
with the math-stat here.  The distribution is *not* symmetric, so it is not crystal clear
to me that what you are doing is correct.  Most likely I am just not looking at the distribution
theory the right way.  In any case, it is probably worth a note and/or reference.  Another
thing that would make me happy (if it works) is to validate the 2-sided test by performing
a (degenerate) Chi-Square test.  Could be what I am missing is that in the setup here these
are not the same.  I will dig into this a little but references are appreciated.
4. I assume the reference values in the tests come from R?  You should make it clear where
the come from.

Thanks again for the patch!

                  
> Add binomial test
> -----------------
>
>                 Key: MATH-1034
>                 URL: https://issues.apache.org/jira/browse/MATH-1034
>             Project: Commons Math
>          Issue Type: Wish
>    Affects Versions: 3.2
>            Reporter: Thorsten Schäfer
>            Priority: Minor
>         Attachments: binomialTest.patch, binomialTest.patch
>
>
> A binomial test would be a nice addition to commons-math. I might supply a patch in the
near future. I guess the interface should be similar to the other tests, i.e., a method to
get the p-value and a method returning a boolean indicating reject/non-reject.
> Is there a policy about using Enumerations in commons-math? For instance, in R you can
test two-sided, less or greater. This could be done using an enumeration in Java, but I'm
not sure if this is discouraged for backward compatibility reasons...

--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira

Mime
View raw message