Testing the ratio of two Poisson rates

被引:75
作者
Gu, Kangxia [1 ]
Ng, Hon Keung Tony [1 ]
Tang, Man Lai [2 ]
Schucany, William R. [1 ]
机构
[1] So Methodist Univ, Dept Stat Sci, Dallas, TX 75275 USA
[2] Hong Kong Baptist Univ, Dept Math, Kowloon, Hong Kong, Peoples R China
关键词
asymptotic tests; conditional test; constrained maximum likelihood estimation; level of significance; mid-p; Monte Carlo simulation; power;
D O I
10.1002/bimj.200710403
中图分类号
Q [生物科学];
学科分类号
07 ; 0710 ; 09 ;
摘要
In this paper we compare the properties of four different general approaches for testing the ratio of two Poisson rates. Asymptotically normal tests, tests based on approximate p-values, exact conditional tests, and a likelihood ratio test are considered. The properties and power performance of these tests are studied by a Monte Carlo simulation experiment. Sample size calculation formulae are given for each of the test procedures and their validities are studied. Some recommendations favoring the likelihood ratio and certain asymptotic tests are based on these simulation results. Finally, all of the test procedures are illustrated with two real life medical examples.
引用
收藏
页码:283 / 298
页数:16
相关论文
共 26 条
[1]  
[Anonymous], 1988, Order Restricted Inference
[2]  
[Anonymous], 1952, ANN I STAT MATH, DOI DOI 10.1007/BF02949788
[3]   THE TRANSFORMATION OF POISSON, BINOMIAL AND NEGATIVE-BINOMIAL DATA [J].
ANSCOMBE, FJ .
BIOMETRIKA, 1948, 35 (3-4) :246-254
[4]  
BIRNBAUM A, 1953, BIOMETRIKA, V40, P447, DOI 10.1093/biomet/40.3-4.447
[5]  
BROWNLEE K, 1967, STAT THEORY METHODOL
[6]  
Cox D., 1966, STAT ANAL SERIES EVE
[7]   COMPARISON OF 2 POISSON-DISTRIBUTED OBSERVATIONS [J].
DETRE, K ;
WHITE, C .
BIOMETRICS, 1970, 26 (04) :851-&
[8]   ORDER RESTRICTED STATISTICAL TESTS ON MULTINOMIAL AND POISSON PARAMETERS - THE STARSHAPED RESTRICTION [J].
DYKSTRA, RL ;
ROBERTSON, T .
ANNALS OF STATISTICS, 1982, 10 (04) :1246-1252
[9]   POWER COMPUTATIONS FOR DESIGNING COMPARATIVE POISSON TRIALS [J].
GAIL, M .
BIOMETRICS, 1974, 30 (02) :231-237
[10]   Confidence limits for the ratio of two rates based on likelihood scores: non-iterative method [J].
Graham, PL ;
Mengersen, K ;
Morton, AP .
STATISTICS IN MEDICINE, 2003, 22 (12) :2071-2083