Comparing the means of two independent groups

Recently, CRESSIE and WHITFORD (1986) showed that Welch's test of H0 :μ1 = μ2 can be biased, under nonnormality, where μ1 and μ2 are the means of two independent treatment groups. They suggested, therefore, that a two-sample analog of Johnson's test be used instead. One goal in this paper is to examine the extent to which a two-sample analog of Johnson's test improves upon Welch's technique in terms of Type I errors and power when sample sizes are small or moderately large. Several alternative procedures are also considered including an additional modification of Johnson's procedure, a procedure suggested by DUNNETT (1982) that uses Tiku's modified maximum likelihood estimate with 10% trimming, two versions of Efron's bootstrap, and a test recently proposed by WILCOX (1989). The paper also describes situations where Welch's procedure is not robust in terms of Type I errors. This is important because based on results currently available, Welch's procedure is thought to be nonrobust in terms of power, but robust in terms of Type I errors.

[1]  John C. W. Rayner,et al.  Welch's approximate solution for the Behrens-Fisher problem , 1987 .

[2]  A. Gayen.  Significance of difference between the means of two non-normal samples. , 1950, Biometrika.

[3]  N. J. Johnson,et al.  Modified t Tests and Confidence Intervals for Asymmetrical Populations , 1978 .

[4]  A. Lee,et al.  Levels of significance of some two-sample tests wkem observations are from compound normal distributions , 1976 .

[5]  Egon S. Pearson,et al.  Relation between the shape of population distribution and the robustness of four simple test statistics , 1975 .

[6]  T. Micceri.  The unicorn, the normal curve, and other improbable creatures. , 1989 .

[7]  Pandu R. Tadikamalla,et al.  A Probability Distribution and its Uses in Fitting Data , 1979 .

[8]  B. L. Welch.  THE SIGNIFICANCE OF THE DIFFERENCE BETWEEN TWO MEANS WHEN THE POPULATION VARIANCES ARE UNEQUAL , 1938 .

[9]  T. Donaldson.  Robustness of the F-Test to Errors of Both Kinds and the Correlation Between the Numerator and Denominator of the F-Ratio , 1968 .

[10]  Philip H. Ramsey.  Exact Type 1 Error Rates for Robustness of Student's t Test with Unequal Variances , 1980 .

[11]  M. Tiku,et al.  Estimating the mean and standard deviation from a censored normal sample. , 1967, Biometrika.

[12]  G. S. James.  THE COMPARISON OF SEVERAL GROUPS OF OBSERVATIONS WHEN THE RATIOS OF THE POPULATION VARIANCES ARE UNKNOWN , 1951 .

[13]  Anthony C. Davison,et al.  Saddlepoint approximations in resampling methods , 1988 .

[14]  D. Gronow.  Non-normality in two-sample t-tests , 1953 .

[15]  H. J. Whitford,et al.  How to Use the Two Sample t‐Test , 1986 .

[16]  Charles W. Dunnett,et al.  Robust multiple comparisons , 1982 .

[17]  R. Fisher,et al.  148: Moments and Cumulants in the Specification of Distributions. , 1938 .

[18]  Adjusting for Unequal Variances When Comparing Means in One-Way and Two-Way Fixed Effects ANOVA Models , 1989 .

[19]  M. Tiku.  Robust statistics for testing equality of means or variances , 1982 .

[20]  Morton B. Brown,et al.  The Small Sample Behavior of Some Statistics Which Test the Equality of Several Means , 1974 .