Graphical Procedures for Multiple Comparisons Under General Dependence
成果类型：
Article
署名作者：
Bennett, Christopher J.; Thompson, Brennan S.
署名单位：
Toronto Metropolitan University
刊物名称：
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
ISSN/ISSBN：
0162-1459
DOI：
10.1080/01621459.2015.1093941
发表日期：
2016
页码：
1278-1288
关键词：
摘要：
It has been more than half a century since Tukey first introduced graphical displays that relate nonoverlap of confidence intervals to statistically significant differences between parameter estimates. In this article, we show how Tukey's graphical overlap procedure can be modified to accommodate general forms of dependence within and across samples. We also develop a procedure that can be used to more effectively resolve rankings within the tails of the distributions of parameter values, thereby generalizing existing methods for multiple comparisons with the best: We show that these new procedures retain the simplicity of Tukey's original procedure, while maintaining asymptotic control of the familywise error rate under very general conditions. Simple examples are used throughout to illustrate the procedures. Supplementary materials for this article are available online.