Evaluating the Anderson-Darling Distribution
Except for n = 1, only the limit as n approaches infinity for the distribution of the Anderson-Darling test for uniformity has been found, and that in so complicated a form that published values for a few percentiles had to be determined by numerical integration, saddlepoint or other approximation m...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Foundation for Open Access Statistics
2004-02-01
|
Series: | Journal of Statistical Software |
Online Access: | http://www.jstatsoft.org/index.php/jss/article/view/2321 |
id |
doaj-28d8aa763da847618c0b35a5a1b92af5 |
---|---|
record_format |
Article |
spelling |
doaj-28d8aa763da847618c0b35a5a1b92af52020-11-25T00:15:34ZengFoundation for Open Access StatisticsJournal of Statistical Software1548-76602004-02-01911510.18637/jss.v009.i02925Evaluating the Anderson-Darling DistributionGeorge MarsagliaJohn MarsagliaExcept for n = 1, only the limit as n approaches infinity for the distribution of the Anderson-Darling test for uniformity has been found, and that in so complicated a form that published values for a few percentiles had to be determined by numerical integration, saddlepoint or other approximation methods. We give here our method for evaluating that asymptotic distribution to great accuracy--directly, via series with two-term recursions. We also give, for any particular n, a procedure for evaluating the distribution to the fourth digit, based on empirical CDF's from samples of size 1010 .http://www.jstatsoft.org/index.php/jss/article/view/2321 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
George Marsaglia John Marsaglia |
spellingShingle |
George Marsaglia John Marsaglia Evaluating the Anderson-Darling Distribution Journal of Statistical Software |
author_facet |
George Marsaglia John Marsaglia |
author_sort |
George Marsaglia |
title |
Evaluating the Anderson-Darling Distribution |
title_short |
Evaluating the Anderson-Darling Distribution |
title_full |
Evaluating the Anderson-Darling Distribution |
title_fullStr |
Evaluating the Anderson-Darling Distribution |
title_full_unstemmed |
Evaluating the Anderson-Darling Distribution |
title_sort |
evaluating the anderson-darling distribution |
publisher |
Foundation for Open Access Statistics |
series |
Journal of Statistical Software |
issn |
1548-7660 |
publishDate |
2004-02-01 |
description |
Except for n = 1, only the limit as n approaches infinity for the distribution of the Anderson-Darling test for uniformity has been found, and that in so complicated a form that published values for a few percentiles had to be determined by numerical integration, saddlepoint or other approximation methods. We give here our method for evaluating that asymptotic distribution to great accuracy--directly, via series with two-term recursions. We also give, for any particular n, a procedure for evaluating the distribution to the fourth digit, based on empirical CDF's from samples of size 1010 . |
url |
http://www.jstatsoft.org/index.php/jss/article/view/2321 |
work_keys_str_mv |
AT georgemarsaglia evaluatingtheandersondarlingdistribution AT johnmarsaglia evaluatingtheandersondarlingdistribution |
_version_ |
1725386173167173632 |