Re: [boost] [Math Statistical Distributions] Hypergeometricdistribution

From: Paul A Bristow (pbristow_at_[hidden])
Date: 2008-05-06 05:08:12

>-----Original Message-----
>From: boost-bounces_at_[hidden] 
>[mailto:boost-bounces_at_[hidden]] On Behalf Of Paul A Bristow
>Sent: 05 May 2008 11:19
>To: boost_at_[hidden]
>Subject: Re: [boost] [Math Statistical Distributions] 
>Hypergeometricdistribution

>>Do you have any plans to add support for the hypergeometric 
>>distribution?
>>That distribution is important for the Fisher exact test for
>>independence in a 2x2 table.
>
>A brief glance shows that Wikipedia lacks a formula for the cdf
>
>but http://portal.acm.org/citation.cfm?id=151271.151274 looks promising
>
>An accurate computation of the hypergeometric distribution function
>Full text 	pdf formatPdf (676 KB)
>Source 	ACM Transactions on Mathematical Software (TOMS) archive
>Volume 19 ,  Issue 1  (March 1993) table of contents
>Pages: 33 - 43  
>Year of Publication: 1993
>ISSN:0098-3500
>Author 	
>Trong Wu 	 Southern Illinois Univ., Edwardsville

A brief study of this (kindly provided by Oliver Seiler) shows it to be 'interesting' - but outstandingly accurate.

>MathCAD appears to offer the density, cumulative and inverse, 
>so this could provide some independent test values.

K Krishnamoorthy, Handbook of Statistical distributions with applications, in Chapter 4 deals with this distribution and also gives
FORTRAN algorithms, but Wu (see above ref) shows that these approximations can be spectacularly inaccurate at times.

So this (and other distributions) might be a good GSoC?

Paul

---
Paul A Bristow
Prizet Farmhouse, Kendal, Cumbria UK LA8 8AB
[phone] & SMS, Mobile [phone] & SMS
pbristow_at_[hidden]