The power to detect main and interaction effects in a factorial design was determined when the Bonferroni method was used to control the overall rate of Type I error at a conventional five percent level. For sample sizes typical of educational research, the power of this procedure is shown to be considerably less than that of recommended standards. Alternative applications of the Bonfer-roni procedure are illustrated and discussed.
Get full access to this article
View all access options for this article.
References
1.
Cochran, W. G. and Cox, G. M. (1957). Experimental designs. (2nd Ed.) New York: Wiley.
2.
Cohen, J. (1969). Statistical power analysis for the behavioral sciences. New York: Academic Press.
3.
Gabriel, K. R. (1964). A procedure for testing the homogeneity of all sets of means in analysis of variance. Biometrics, 20, 459-477.
4.
Hastings, C., Jr. (1955). Approximations for digital computers. Princeton: Princeton University Press.
5.
Kirk, R. E. (1982). Experimental design: Procedures for the behavioral sciences. (2nd Ed.) Belmont, CA: Brooks/Cole.
6.
Koele, P. (1982). Calculating power in analysis of variance. Psychological Bulletin, 94, 513-516.
7.
Olejnik, S. F. (1984). Planning educational research: Determining the necessary sample size. Journal of Experimental Education, 53(1), 40-48.
8.
Rosenthal, R. and Rubin, D. B. (1984). Multiple contrasts and ordered Bonferroni procedures. Journal of Educational Psychology, 76, 1028-1034.
9.
Ryan, T. A. (1985). "Ensemble-adjusted p values": How are they to be weighted?Psychological Bulletin, 97, 521-526.
10.
Scheffe, H. (1959). The analysis of variance. New York: Wiley.
11.
Severo, N. C. and Zelen, M. (1960). Normal approximation to the chi-square and noncentral F probability functions. Biometrika, 47, 411-416.
12.
Zelen, M. and Severo, N. C. (1964). Probability functions. In Handbook of mathematical functions (National Bureau of Standards Applied Mathematics Series No. 55). Washington: U.S. Government Printing Office.
