A goodness-of-fit test for exponentiality based on the memoryless property

被引：30

作者：

Ahmad, IA ^{[1
]}

Alwasel, IA

机构：

[1] No Illinois Univ, Div Stat, De Kalb, IL 60115 USA

[2] King Saud Univ, Dept Stat & Operat Res, Riyadh, Saudi Arabia

来源：

JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY | 1999年 / 61卷

关键词：

asymptotic normality; critical values; goodness-of-fit tests; limiting distribution; Monte Carlo methods; power of tests; testing exponentiality;

D O I：

10.1111/1467-9868.00200

中图分类号：

O21 [概率论与数理统计]; C8 [统计学];

学科分类号：

020208 ; 070103 ; 0714 ;

摘要：

In this investigation a test of goodness of fit for exponentiality is proposed. This procedure applies equally whether the scale and/or the location parameters of the distribution are known or not. The limiting null and non-null distributions of the test statistic are normal under minimal conditions. Monte Carlo critical values for small sample sizes are given and the power of the test is calculated for various alternatives showing that it compares favourably relatively to other more complicated published procedures.

引用

页码：681 / 689

页数：9

共 10 条

[1]

AGOSTINO RB, 1986, GOODNESS OF FIT TECH

[2] A SURVEY OF TESTS FOR EXPONENTIALITY [J].