A more powerful test for comparing two Poisson means

被引:111
作者
Krishnamoorthy, K [1 ]
Thomson, J [1 ]
机构
[1] Univ Louisiana, Dept Math, Lafayette, LA 70504 USA
关键词
binomial distribution; exact power; exact size; parametric bootstrap; Poisson distribution; sample size calculation; standardized difference;
D O I
10.1016/S0378-3758(02)00408-1
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
The problem of hypothesis testing about two Poisson means is addressed. The usual conditional test (C-test) and a test based on estimated p-values (E-test) are considered. The exact properties of the tests are evaluated numerically. Numerical studies indicate that the E-test is almost exact because its size seldom exceeds the nominal level, and it is more powerful than the C-test. Power calculations for both tests are outlined. The test procedures are illustrated using two examples. (C) 2002 Elsevier B.V. All rights reserved.
引用
收藏
页码:23 / 35
页数:13
相关论文
共 15 条