The two-stage δ-corrected Kolmogorov-Smirnov test

被引:19
作者
Khamis, HJ [1 ]
机构
[1] Wright State Univ, Ctr Stat Consulting, Dayton, OH 45435 USA
关键词
D O I
10.1080/02664760050003623
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 delta-corrected Kolmogorov-Smirnov test has been shown to be uniformly more powerful than the classical Kolmogorov-Smirnov test for small to moderate sample sizes. However, the delta-corrected test consists of two tests, leading to a slight inflation of the experimentwise type I error rate. The critical values of the delta-corrected test are adjusted to take into account the two-stage nature of the test, ensuring an experimentwise error rate at the nominal level. A power study confirms that the resulting so-called two-stage delta-corrected test is uniformly more powerful than the classical Kolmogorov-Smirnov test, with power improvements of up to 46 percentage points.
引用
收藏
页码:439 / 450
页数:12
相关论文
共 28 条
[1]  
[Anonymous], INGENIORS VETENSKAPS
[2]  
[Anonymous], 2007, Biostatistical analysis
[3]  
[Anonymous], INGENIORS VETENSKAPS
[4]   IN-VITRO REPLICATION OF PLASMIDS CONTAINING HUMAN C-MYC DNA [J].
BERBERICH, S ;
TRIVEDI, A ;
DANIEL, DC ;
JOHNSON, EM ;
LEFFAK, M .
JOURNAL OF MOLECULAR BIOLOGY, 1995, 245 (02) :92-109
[5]  
BLOM G, 1958, STAT EST TRANSFORMED
[6]   RANGE OF DIFFERENCE BETWEEN HYPOTHETICAL DISTRIBUTION FUNCTION AND PYKES MODIFIED EMPIRICAL DISTRIBUTION FUNCTION [J].
BRUNK, HD .
ANNALS OF MATHEMATICAL STATISTICS, 1962, 33 (02) :525-&
[7]  
DURBIN J, 1969, BIOMETRIKA, V56, P1
[8]  
Gibbons J.D., 1985, NONPARAMETRIC STAT I
[9]  
GREEN JR, 1976, J AM STAT ASSOC, V71, P204
[10]  
Gumbel EJ, 1942, BIOMETRIKA, V32, P317