commons-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Luc Maisonobe (JIRA)" <j...@apache.org>
Subject [jira] Commented: (MATH-222) Need way to compute density of distributions
Date Tue, 09 Sep 2008 20:53:44 GMT

    [ https://issues.apache.org/jira/browse/MATH-222?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12629613#action_12629613
] 

Luc Maisonobe commented on MATH-222:
------------------------------------

The first patch has been applied in subversion repository (in 2.0 branch) as of r693598 with
the following changes:
 - the BetaDistributionTest file has been removed (it probably belongs to the second patch)
 - the commons-math.iml file has been removed (it probably depends on a specific development
environment)
 - the patch for pom.xml has been removed (language level are configured using maven.compile.source
and maven.compile.target properties)
 - Apache header has been added to the HasDensityFunction interface
 - Javadoc has been added to the HasDensityFunction interface

Before applying the second patch, I think we would need a Contributor License Agreement (see
[http://www.apache.org/licenses/#clas]. The patch adds a complete class that is almost 200
lines long so I don't think we can include it immediately. Apart from that, this would be
an interesting addition.


> Need way to compute density of distributions
> --------------------------------------------
>
>                 Key: MATH-222
>                 URL: https://issues.apache.org/jira/browse/MATH-222
>             Project: Commons Math
>          Issue Type: New Feature
>            Reporter: Ted Dunning
>         Attachments: MATH-222-with-beta.patch, MATH-222.patch
>
>
> Currently, there are a number of distributions defined in commons math, but the interface
for Distribution and ContinuousDistribution doesn't provide for the computation of the PDF
at a particular point.
> It is common for it to be necessary to compute the density function, for example in the
Metropolis algorithm.
> It is also pretty common for it to be very difficult to compute a density function or
for the density function to be undefined as certain points.  Only the cumulative density is
mathematically assured.
> Thus, I propose to create a new interface HasDensityFunction<T> that requires the
implementation of a double density(T) method.  T is the type of the argument for the density
function which would be Double in the case of most univariate statistics, but could, for instance,
be a vector of doubles for a Dirichlet distribution or a vector of integers for a Multinomial.

-- 
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.


Mime
View raw message