Some Rank Sum Multiple Comparisons Tests
- 1 December 1961
- journal article
- research article
- Published by JSTOR in Biometrics
- Vol. 17 (4), 539-+
- https://doi.org/10.2307/2527854
Abstract
A non-parametric rank sum test is described for the comparison of all pairs of treatments in a completely random design. For this test, one computes the Wilcoxon-Mann-Whitney criterion for all pairs. Significant values are obtained from accompanying tables to give rank sum analogues of parametric test procedures proposed by Tukey, Newman-Keuls, and Duncan.This publication has 8 references indexed in Scilit:
- 163 Query: Error Rates in Multiple ComparisonsBiometrics, 1961
- 161 Note: Corrected Error Rates for Duncan's New Multiple Range TestBiometrics, 1961
- A Rank Sum Test for Comparing All Pairs of TreatmentsTechnometrics, 1960
- A Multiple Comparison Rank Sum Test: Treatments versus ControlBiometrics, 1959
- Multiple Range and Multiple F TestsBiometrics, 1955
- The Use of Ranks in a Test of Significance for Comparing Two TreatmentsBiometrics, 1952
- Individual Comparisons by Ranking MethodsBiometrics Bulletin, 1945
- THE DISTRIBUTION OF RANGE IN SAMPLES FROM A NORMAL POPULATION, EXPRESSED IN TERMS OF AN INDEPENDENT ESTIMATE OF STANDARD DEVIATIONBiometrika, 1939