Mailing-List: contact issues-help@commons.apache.org; run by ezmlm
Precedence: bulk
Reply-To: issues@commons.apache.org
Date: Sat, 25 Feb 2012 20:19:49 +0000 (UTC)
From: =?utf-8?Q?S=C3=A9bastien_Brisard_=28Issue_Comment_Edited=29_=28JIRA=29?=
 <jira@apache.org>
To: issues@commons.apache.org
Message-ID: 
 <305381053.19998.1330201189487.JavaMail.tomcat@hel.zones.apache.org>
In-Reply-To: 
 <847434589.16931.1330119604942.JavaMail.tomcat@hel.zones.apache.org>
Subject: [jira] [Issue Comment Edited] (MATH-753) Better implementation for
 the gamma distribution density function
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: quoted-printable


    [ https://issues.apache.org/jira/browse/MATH-753?page=3Dcom.atlassian.j=
ira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=3D132165=
29#comment-13216529 ]=20

S=C3=A9bastien Brisard edited comment on MATH-753 at 2/25/12 8:19 PM:
-----------------------------------------------------------------

This suits me fine. The only concern I have is that using exp(log( x )) in =
place of x might incur a loss of accuracy. Maybe we should use this substit=
ution only when it is necessary (for large values of alpha and beta). This =
would require a little bit of investigation to find the appropriate thresho=
lds.
               =20
      was (Author: celestin):
    This suits me fine. The only concern I have is that using exp(log(x)) i=
n place of x might incur a loss of accuracy. Maybe we should use this subst=
itution only when it is necessary (for large values of alpha and beta). Thi=
s would require a little bit of investigation to find the appropriate thres=
holds.
                 =20
> Better implementation for the gamma distribution density function
> -----------------------------------------------------------------
>
>                 Key: MATH-753
>                 URL: https://issues.apache.org/jira/browse/MATH-753
>             Project: Commons Math
>          Issue Type: Improvement
>    Affects Versions: 2.2
>            Reporter: Francesco Strino
>            Priority: Minor
>              Labels: improvement, stability
>             Fix For: 2.2
>
>
> The way the density of the gamma distribution function is estimated can b=
e improved.
> It's much more stable to calculate first the log of the density and then =
exponentiate, otherwise the function returns NaN for high values of the par=
ameters alpha and beta.=20
> It would be sufficient to change the public double density(double x) func=
tion at line 204 in the file org.apache.commons.math.distribution.GammaDist=
ributionImpl as follows:
> return Math.exp(Math.log( x )*(alpha-1) - Math.log(beta)*alpha - x/beta -=
 Gamma.logGamma(alpha));=20
> In order to improve performance, log(beta) and Gamma.logGamma(alpha) coul=
d also be precomputed and stored during initialization.

--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrato=
rs: https://issues.apache.org/jira/secure/ContactAdministrators!default.jsp=
a
For more information on JIRA, see: http://www.atlassian.com/software/jira