Abstract
The random effects ANOVA model plays an important role in many psychological studies, but the usual model suffers from at least two serious problems. The first is that even under normality, violating the assumption of equal variances can have serious consequences in terms of Type I errors or significance levels, and it can affect power as well. The second and perhaps more serious concern is that even slight departures from normality can result in a substantial loss of power when testing hypotheses. Jeyaratnam and Othman (1985) proposed a method for handling unequal variances, under the assumption of normality, but no results were given on how their procedure performs when distributions are nonnormal. A secondary goal in this paper is to address this issue via simulations. As will be seen, problems arise with both Type I errors and power. Another secondary goal is to provide new simulation results on the Rust-Fligner modification of the Kruskal-Wallis test. The primary goal is to propose a generalization of the usual random effects model based on trimmed means. The resulting test of no differences among J randomly sampled groups has certain advantages in terms of Type I errors, and it can yield substantial gains in power when distributions have heavy tails and outliers. This last feature is very important in applied work because recent investigations indicate that heavy-tailed distributions are common. Included is a suggestion for a heteroscedastic Winsorized analog of the usual intraclass correlation coefficient.
Similar content being viewed by others
References
Bickel, P. J., & Lehmann, E. L. (1975). Descriptive statistics for nonparametric models II. Location.Annals of Statistics, 3, 1045–1158.
Bowen, R. M., & Huang, M. (1990). A comparison of maximum likelihood with method of moment procedures for separating individual and group effects.Journal of Personality and Social Psychology, 58, 90–94.
Box, G. E. P. (1954). Some theorems on quadratic forms applied in the study of analysis of variance problems, I. Effect of inequality of variance in the one-way model.Annals of Mathematical Statistics, 25, 290–302.
Bradley, J. V. (1978). Robustness?British Journal of Mathematical and Statistical Psychology, 31, 144–152.
Brown, M. B., & Forsythe, A. (1974). The small sample behavior of some statistics which test the equality of several means.Technometrics, 16, 129–132.
Cressie, N. A. C., & Whitford, H. J. (1986). How to use the two samplet-test.Biometrical Journal, 28, 131–148.
Cronbach, L. J., Gleser, G., & Rajaratnam, N. (1972).The Dependability of Behavioral Measurements: Theory of Generalizability for Scores and Profiles. New York: Wiley.
Fenstad, G. U. (1983). A comparison between U and V tests in the Behrens-Fisher problem.Biometrika, 70, 300–302.
Freedman, D. A., & Diaconis, P. (1982). On inconsistent M-estimators.Annals of Statistics, 10, 454–461.
Gleason, J. R. (1993). Understanding elongation: The scale contaminated normal family.Journal of the American Statistical Association, 88, 327–337.
Gollob, H. F. (1991). Methods of estimating individual- and Group-level correlations.Journal of Personality and Social Psychology, 60, 376–381.
Hoaglin, D. C. (1985). Summarizing shape numerically: Theg-and-h distributions. In D. Hoaglin, F. Mosteller, & J. Tukey (eds.),Exploring data tables, trends, and shapes. New York: Wiley.
Hogg, R. V. (1974). Adaptive robust procedures: A partial review and some suggestions for future applications and theory.Journal of the American Statistical Association, 69, 909–922.
Huber, P. J. (1981).Robust statistics. New York: Wiley.
International Mathematical and Statistical Libraries (1987). Library I, Vol. II. Houston: Author.
Jeyaratnam, S., & Othman, A. B. (1985). Test of hypothesis in one-way random effects model with unequal error variances.Journal of Statistical Computation and Simulation, 21, 51–57.
Kenny, D., & La Voie, L. (1985). Separating individual and group effects.Journal of Personality and Social Psychology, 48, 339–348.
Micceri, T. (1989). The unicorn, the normal curve, and other improbable creatures.Psychological Bulletin, 105, 156–166.
Oshima, T. C., & Algina, J. (1992). Type I error rates for James's second-order test and Wilcox'sH m test under heterocedasticity and nonnormality.British Journal of Mathematical and Statistical Psychology, 45, 255–264.
Ramberg, J. S., Tadikamalla, P. R., Dudewicz, E. J., & Mykytka, E. F. (1978). A probability distribution and its uses in fitting data.Technometrics, 21, 201–214.
Randles, R. H., & Wolfe, D. A. (1979).Introduction to the Theory of Nonparametric Statistics. New York: Wiley.
Rao, P. S. R. S., Kaplan, J., & Cochran, W. G. (1981). Estimators for the one-way random effects model with unequal error variances.Journal of the American Statistical Association, 76, 89–97.
Rogan, J., & Keselman, H. J. (1977). Is the ANOVAF-test robust to variance heterogeneity when sample sizes are equal?: An investigation via a coefficient of variation.American Educational Research Journal, 14, 493–498.
Rosenberger, J. L., & Gasko, M. (1983). Comparing location estimators: Trimmed means, medians and trimean. In D. Hoaglin, F. Mosteller, & J. Tukey (eds.),Understanding robust and exploratory data analysis (pp. 297–336). New York: Wiley.
Rust, S. W., & Fligner, M. A. (1984). A modification of the Kruskal-Wallis statistic for the generalized Behrens-Fisher problem.Communications in Statistics—Theory and Methods, 13, 2013–2027.
Sawilowsky, S. S., & Blair, R. C. (1992). A more realistic look at the robustness and Type II error properties of thet test to departures from normality.Psychological Bulletin, 111, 352–360.
Scheffé, H. (1959).The Analysis of Variance. New York: Wiley.
Staudte, R. G., & Sheather, S. J. (1990).Robust Estimation and Testing. New York: Wiley.
Tomarken, A., & Serlin, R. (1986). Comparison of ANOVA alternatives under variance heterogeneity and specific noncentrality structures.Psychological Bulletin, 99, 90–99.
Tukey, J. W. (1960). A survey of sampling from contaminated normal distributions. In I. Olkin, et al. (eds.),Contributions to probability and statistics. Stanford, CA: Stanford University Press.
Welch, B. L. (1938). The significance of the difference between two means when the population variances are unequal.Biometrika, 29, 350–362.
Westfall, P. (1988). Robustness and power of tests for a null variance ratio.Biometrika, 75, 20–35.
Wilcox, R. R. (1987). New designs in the analysis of variance.Annual Review of Psychology, 38, 29–60.
Wilcox, R. R. (1990). Comparing the means of two independent groups.Biometrical Journal, 32, 771–780.
Wilcox, R. R. (1992). Comparing one-stepM-estimators of location corresponding to two independent groups.Psychometrika, 57, 141–154.
Wilcox, R. R. (1993a). Comparing one-stepM-estimators of location when there are more than two groups.Psychometrika, 58, 71–78.
Wilcox, R. R. (1993b). Some results on a Winsorized correlation coefficient.British Journal of Mathematical and Statistical Psychology, 46, 339–349.
Wilcox, R. R. (in press). Some results on the Tukey-McLaughlin and Yuen methods for trimmed means when distributions are skewed.Biometrical Journal.
Wilcox, R. R., Charlin, V., & Thompson, K. L. (1986). New Monte Carlo results on the robustness of the ANOVA F, W andF* statistics.Communications in Statistics—Simulation and Computation, 15, 933–944.
Yuen, K. K. (1974). The two sample trimmedt for unequal population variances.Biometrika, 61, 165–170.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Wilcox, R.R. A one-way random effects model for trimmed means. Psychometrika 59, 289–306 (1994). https://doi.org/10.1007/BF02296126
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF02296126