On distribution-free multiple comparisons in the one-way analysis of variance
- 1 January 1991
- journal article
- research article
- Published by Taylor & Francis Ltd in Communications in Statistics - Theory and Methods
- Vol. 20 (1), 127-139
- https://doi.org/10.1080/03610929108830487
Abstract
Two methods are described for conducting distribution-free multiple comparisons of k > 2 populations. The Steel-Dwass method, based on pairwise rankings, possesses several desirable properties that are investigated. New large sample approximations are given, that are less conservative than those of the Bonferroni type suggested by Dunn (1964), and small sample tables for k = 3 populations are provided. Simultaneous confidence intervals are derived for all the pairwise location differences. Finally, an example illustrates the methodology.Keywords
This publication has 10 references indexed in Scilit:
- Extended tables of the exact distribution of a rank statistic for all treatments multiple comparisons in one-way layout designsCommunications in Statistics - Theory and Methods, 1987
- A Proof of the Conjecture that the Tukey-Kramer Multiple Comparisons Procedure is ConservativeThe Annals of Statistics, 1984
- Simultaneous Statistical InferencePublished by Springer Science and Business Media LLC ,1981
- $(k - 1)$-Mean Significance Levels of Nonparametric Multiple Comparisons ProceduresThe Annals of Statistics, 1980
- On the Asymptotic Equivalence of Two Ranking Methods for $K$-Sample Linear Rank StatisticsThe Annals of Statistics, 1977
- Multiple-Unit Activity in the Pineal Gland of the Japanese Quail: Spontaneous Firing and Responses to Photic StimulationsNeuroendocrinology, 1974
- Multiple Comparisons Using Rank SumsTechnometrics, 1964
- 163 Query: Error Rates in Multiple ComparisonsBiometrics, 1961
- A Rank Sum Test for Comparing All Pairs of TreatmentsTechnometrics, 1960
- Extension of Multiple Range Tests to Group Means with Unequal Numbers of ReplicationsBiometrics, 1956