This paper includes 3 tables for quick power estimates that require no computation for the most common designs involving comparisons of 2 and 3 means in ANOVA and ANCOVA situations. Power can be estimated for (from .1σ to 1σ) for 4 effect sizes at alpha levels from .01 to .20, for samples sizes from 5 to 400 per group, and for directional and nondirectional tests.
Get full access to this article
View all access options for this article.
References
1.
Brewer, J.K.On the power of statistical tests. American Educational Research Journal, 1972, 9, 391-401.
2.
Cohen, J.Statistical power analysis for the behavioral sciences. New York: Academic Press, 1969.
3.
Cohen, J.Statistical power analysis and research results. American Educational Research Journal, 1973, 10, 225-229.
4.
Cohen, S.A., & Hyman, J.S.How come so many hypotheses in educational research are supported? (A modest proposal). Educational Researcher, 1979, 8(11), 12-16.
5.
Glass, G.V., & Stanley, J.C.Statistical methods in education and psychology. Englewood Cliffs, N.J.: Prentice-Hall, 1970 .
6.
Hopkins, K.D.Preventing the number-one misinterpretation of behavioral research, or how to increase statistical power. Journal of Special Education , 1973, 7, 103-107.
7.
Hopkins, K.D., & Hopkins, B.R.The effect of the reliability of the dependent variable on power. Journal of Special Education, 1979, 13, 463-466.
8.
Winer, B.J.Statistical principles in experimental design (2nd ed.). New York: McGraw Hill, 1971.
