Stepwise multiple tests for successive comparisons of treatment effects

    Authors

    W. Liu;P. N. Somerville

    Comments

    Authors: contact us about adding a copy of your work at STARS@ucf.edu

    Abbreviated Journal Title

    Comput. Stat. Data Anal.

    Keywords

    critical constants; familywise error rate; multiple comparisons; multivariate-t distribution; simultaneous confidence intervals; Computer Science, Interdisciplinary Applications; Statistics &; Probability

    Abstract

    Suppose that the k treatments under comparison are ordered in a certain way. For example, they may be a sequence of increasing dose levels of a drug. It is interesting to look directly at the successive differences between the treatment effects mu(i)'s, namely the set of differences mu(2) - mu(1), mu(3) - mu(2)...,mu(k) - mu(k-1). Lee and Spurrier (J, Statist. Plann. Inference 43 (1995) 323) propose a one-sided and a two-sided simultaneous confidence interval procedures for making successive comparisons between treatments. In this paper we develop step-down and step-up tests for testing the families of hypotheses H-i0: mu(i+1) - mu(i) = 0 vs H-ia: mu(i+1) > 0, i = 1,...,k - I (one-sided alternatives) H-i0: mu(i+1) - mu(i) = 0 vs H-ia: mu(i+1) - mu(i) not equal 0, i = 1,...,k - 1 (two-sided alternatives) These stepwise tests are uniformly more powerful than the simultaneous confidence interval procedures in terms of rejection of the null hypotheses, though the simultaneous confidence interval procedures provide information on the magnitudes of the mu(i+1) - mu(i)'s. The critical constants required for applying these multiple tests are provided, and the tests are illustrated with a numerical example. (C) 2003 Published by Elsevier B.V.

    Journal Title

    Computational Statistics & Data Analysis

    Volume

    46

    Issue/Number

    1

    Publication Date

    1-1-2004

    Document Type

    Article

    Language

    English

    First Page

    189

    Last Page

    199

    WOS Identifier

    WOS:000220929400012

    ISSN

    0167-9473

    Share

    COinS