Pairwise Multiple Comparisons in the Homogeneous Variance, Unequal Sample Size Case

Abstract The effect of unequal ni on the error rates of six procedures for pair-wise multiple comparisons beteen k treatment means with homogeneous variances was studied by computer simulation. A commonly used method, attributed to Kramer (1956) but suggested also by Tukey (1953), was found to have error rates less than the nominal value α for several patterns of inequality in the sample sizes, at least when the variations in ni were moderately large. A method that substitutes the harmonic mean sample size for n in Tukey's T method had excessively high error rates. Other methods proposed more recently in the literature were conservative relative to the Tukey-Kramer method. Thus, the Tukey-Kramer method is recommended for use in the unequal sample size, homogeneous variance situation.

[1]  H. Keselman,et al.  A Comparison of the Modified-Tukey and Scheffé Methods of Multiple Comparisons for Pairwise Contrasts , 1978 .

[2]  H. Ury,et al.  Tables of the Studentized Maximum Modulus Distribution and an Application to Multiple Comparisons Among Means , 1979 .

[3]  Q. Mcnemar.  Note on the sampling error of the difference between correlated proportions or percentages , 1947, Psychometrika.

[4]  Y. Hochberg.  An Extension of the T‐Method to General Unbalanced Models of Fixed Effects , 1975 .

[5]  B. J. Winer.  Statistical Principles in Experimental Design , 1992 .

[6]  M. R. Stoline.  Tables of the Studentized Augmented Range and Applications to Problems of Multiple Comparison , 1978 .

[7]  Yosef Hochberg,et al.  On Improved Extensions of the T-Method of Multiple Comparisons for Unbalanced Designs , 1978 .

[8]  Rupert G. Miller.  Simultaneous Statistical Inference , 1966 .

[9]  D. Newman,et al.  THE DISTRIBUTION OF RANGE IN SAMPLES FROM A NORMAL POPULATION, EXPRESSED IN TERMS OF AN INDEPENDENT ESTIMATE OF STANDARD DEVIATION , 1939 .

[10]  Paul A. Games,et al.  An Addendum to “A Comparison of the Modified-Tukey and Scheffé Methods of Multiple Comparisons for Pairwise Contrasts” , 1979 .

[11]  Gary C. Ramseyer,et al.  The Robustness of the Studentized Range Statistic to Violations of the Normality and Homogeneity of Variance Assumptions , 1973 .

[12]  F. N. David,et al.  Principles and procedures of statistics. , 1961 .

[13]  Emil Spjøtvoll,et al.  An Extension of the T-Method of Multiple Comparison to Include the Cases with Unequal Sample Sizes , 1973 .

[14]  Clyde Young Kramer,et al.  Extension of multiple range tests to group means with unequal numbers of replications , 1956 .

[15]  K. Ruben Gabriel,et al.  A Simple Method of Multiple Comparisons of Means , 1978 .

[16]  Z. Šidák.  Rectangular Confidence Regions for the Means of Multivariate Normal Distributions , 1967 .

[17]  L. Brown.  A Proof That Kramer's Multiple Comparison Procedure for Differences Between Treatment Means Is Level-α for 3, 4, or 5 Treatments , 1979 .

[18]  W. G. Cochran.  The comparison of percentages in matched samples. , 1950, Biometrika.

[19]  Yosef Hochberg,et al.  Some generalizations of the T-method in simultaneous inference , 1974 .

[20]  Rupert G. Miller,et al.  Developments in Multiple Comparisons 1966–1976 , 1977 .