Using randomly generated samples from populations having varying rhos,
different shapes of distributions, and varying sample sizes, the effects of
violating the population normality assumption underlying r were examined.
Results indicate that the normality assumption underlying r is robust (i. e., that
violation of the population normality assumption does not seriously alter the
interpretation of r). Violation of the population normality assumption
appears, therefore, to be insufficient reason to deny r a place as a major tool
for sociological analysis.
Get full access to this article
View all access options for this article.
References
1.
Bartlett, M.S. (1937) "Properties of sufficiency and statistical tests ." Proceedings of the Royal Academy160: 268-282.
2.
Blalock, H.M. (1972) Social Statistics. New York : McGraw-Hill.
3.
Boneau, C.A. (1960) "The effects of violations of assumptions underlymg the t test." Psych. Bull.57: 49-64.
4.
Box, G.E.P. and S.L. Anderson (1955) "Permutation theory in the derivation of robust criticism and the study of departures from assumption." J. of the Royal Stat. Society17: 1-34.
5.
David, F.N. and N.L. Johnson (1951) "The effect of non-normality on the power function and the F test in the analysis of variance." Biometrika38: 43-57.
6.
Gayen, A.K. (1950a) "The distribution of the variance ratio in random samples of any size drawn from non-normal universes." Biometrika37: 236-255.
7.
--- ( 1950b) "Significance of difference between the means of two non-normal samples." Biometrika37: 299-408.
8.
Kendall, M.G. and A. Stuart (1961) The Advanced Theory of Statistics. New York: Hafner.
9.
Lindquist, E.F. (1953) The Norton Study of the Effects of Non-Normality and Heterogeneity of Variance, Design and Analysis of Experiments in Psychology and Education. Boston: Houghton Mifflin.
10.
Norton, D.W. (1952) "An empirical investigation of some effects of non-normality and heterogeneity on the F-distribution." Ph.D. dissertation. State University of Iowa.
11.
Pearson, E.S. (1931) "The analysis of variance in the case of non-normal variation." Biometrika30: 114-133.