Effect of tail weight and outliers on power and type-i error of robust permutation tests for location
作者:
Allie Keller-Mcnulty,
James j Higgins,
期刊:
Communications in Statistics - Simulation and Computation
(Taylor Available online 1987)
卷期:
Volume 16,
issue 1
页码: 17-35
ISSN:0361-0918
年代: 1987
DOI:10.1080/03610918708812575
出版商: Marcel Dekker, Inc.
数据来源: Taylor
摘要:
A simulation study on two sample robust permutation tests for location is presented. The robust statistics studied fall into three categories; L-estimators, M-estimators, and adaptive estimators. The normal, Laplace, Cauchy, and mixture of normal distributions are used to investigate the power of the robust permutation tests, and normal distributions contaminated with outliers are used to investigate the effect of outliers on type-I error rates. The Wilcoxon rank sum test is used as a standard against which to measure the performance of the robust permutation tests
点击下载:
PDF (501KB)
返 回