Introductory statistics textbooks in psychology, education, and social sciences have contributed to the belief that nonparametric tests, such as the Wilcoxon-Mann-Whitney test, are effective against violations of both normality and homogeneity of variance. The present paper emphasizes that, although rank methods often are useful when samples are obtained from heavy-tailed, nonnormal distributions, they are influenced by unequal variances just like parametric tests. Computer programs are now available to perform modified t tests based on unequal sample variances, in which degrees of freedom and critical values are altered from sample to sample. These procedures, although neglected for many years because they are computationally complex, are far more effective than nonparametric methods in protecting against violation of homogeneity of variance.
Get full access to this article
View all access options for this article.
References
1.
BlairR. C.HigginsJ. J. (1980) A comparison of the power of Wilcoxon's rank-sum statistic to that of Student's t under various non-normal distributions. Journal of Educational Statistics, 5, 309–335.
2.
BoxG. E. P.MullerM. (1958) A note on the generation of random normal deviates. Annals of Mathematical Statistics, 29, 610–611.
3.
CochranW. G.CoxG. M. (1957) Experimental designs. (2nd ed.) New York: Wiley.
4.
ConoverW. J. (1980) Practical nonparametric statistics. (2nd ed.) New York: Wiley.
5.
ConoverW. J.ImanR. L. (1981) Rank transformations as a bridge between parametric and nonparametric statistics. The American Statistician, 35, 124–129.
6.
FreundJ. E.WalpoleR. E. (1987) Mathematical statistics. Englewood Cliffs, NJ: Prentice-Hall.
7.
GibbonsJ. D.ChakrabortiS. (1991) Comparisons of the Mann-Whitney, Student's t, and alternate t tests for means of normal distributions. Journal of Experimental Education, 258–267.
8.
GlassG.PeckhamPSandersJ. (1972) Consequences of failure to meet assumptions underlying the fixed effects analysis of variance and covariance. Review of Educational Research, 42, 237–288
9.
HampelF. R.RonchettiE. M.RousseeuwP. J.StahelW. A. (1986) Robust statistics: The approach based on influence functions. New York: Wiley.
10.
HodgesJ.LehmannE. (1956) The efficiency of some nonparametric competitors of the t-test. Annals of Mathematical Statistics, 21, 324–335.
11.
HopkinsK. D.GlassG. V.HopkinsB. R. (1987) Basic statistics for the behavioral sciences. (2nd ed.) Englewood Cliffs, NJ: Prentice-Hall.
12.
HowellD. C. (1987) Statistical methods for psychology. (2nd ed.) Boston, MA: Duxbury Press.
13.
HsuP. L. (1938) Contributions to the theory of “Student's” t-test as applied to the problem of two samples. Statistical Research Memoirs, 2, 1–24.
14.
KeselmanH. J.RoganJ. C.Feir-WalshB. J. (1977) An evaluation of some nonparametric and parametric tests for location equality. British Journal of Mathematical and Statistical Psychology, 30, 213–221.
15.
KirkR. E. (1982) Experimental design. (2nd ed.) Monterey, CA: Brooks/Cole.
16.
LewisP. A. W.GoodmanA. S.MillerJ. M. (1969) A pseudorandom number generator for the System 360. IBM Systems Journal, 8, 136–146.
17.
LewisP. A. W.OravE. J. (1989) Simulation methodology for statisticians, operations analysts, and engineers. Vol. 1. Pacific Grove, CA: Wadsworth.
18.
LoftusG. R.LoftusE. F. (1988) Essence of statistics. (2nd ed.) Monterey, CA: Brooks/Cole.
19.
MarsagliaG.BrayT. A. (1964) A convenient method for generating normal variables. SIAM Review, 6, 260–264.
20.
MicceriT. (1989) The unicorn, the normal curve, and other improbable creatures. Psychological Bulletin, 105, 156–166.
21.
PaganoR. R. (1986) Understanding statistics in the behavioral sciences. (2nd ed.) St. Paul, MN: West.
22.
PrattJ. W. (1964) Robustness of some procedures for the two-sample location problem. Journal of the American Statistical Association, 59, 665–680.
23.
SatterthwaiteF. E. (1946) An approximate distribution of estimates of variance components. Biometrics Bulletin, 2, 110–114.
24.
SchefféH. (1959) The analysis of variance. New York: Wiley.
25.
ShavelsonR. J. (1988) Statistical reasoning for the behavioral sciences. (2nd ed.) Needham Heights, MA: Allyn & Bacon.
26.
TomarkenA. J.SerlinR. C. (1986) Comparison of ANOVA alternatives under variance heterogeneity and specific noncentrality structures. Psychological Bulletin, 99, 90–99.
27.
Van der VaartH. R. (1961) On the robustness of Wilcoxon's two-sample test. In de JonegeH. (Ed.), Quantitative methods in pharmacology. New York: Interscience. Pp. 140–158.
28.
WelchB. L. (1938) The significance of the difference between two means when the population variances are unequal. Biometrika, 29, 350–362.
29.
WelchB. L. (1947) The generalization of Student's problem when several different population variances are involved. Biometrika, 34, 29–35.
30.
WinerB. J. (1971) Statistical principles in experimental design. (2nd ed.) New York: McGraw-Hill.
31.
ZimmermanD. W. (1987) Comparative power of the Student t-test and Mann-Whitney U test for unequal sample sizes and variances. Journal of Experimental Education, 55, 171–174.
32.
ZimmermanD. W.WilliamsR. H. (1988) Power comparisons of the Student t-test and two approximations when variances and sample sizes are unequal. Journal of the Indian Society of Agricultural Statistics, 41, 206–217.
33.
ZimmermanD. W.ZumboB. D. (in press) The relative power of parametric and nonparametric statistical methods. In KerenG.LewisC. (Eds.), Methodological and quantitative issues in the analysis of psychological data. Hillsdale, NJ: Erlbaum.
