This article evaluates power and Type I error probabilities for a modified Fisher exact test for homogeneity of response probabilities in 2 × 2 tables. The original Fisher exact test and the Pearson chi-square are employed as standards for comparison. The continuity-corrected Fisher statistic is shown to be considerably more powerful than the uncorrected Fisher exact test, while it is less often nonconservatively biased than the Pearson chi-square.
Get full access to this article
View all access options for this article.
References
1.
CamilliG.HopkinsK. D.Applicability of chi-square to 2 × 2 contingency tables with small expected cell frequencies. Psychological Bulletin, 1978, 85, 163–167.
2.
CohenJ.Statistical power analysis for the behavioral sciences. New York: Academic Press, 1977.
3.
DetreK.WhiteC.The comparison of two Poisson-distributed variables. Biometrics, 1970, 26, 851–854.
4.
EisenhartC.Inverse sine transformation of proportions. In Statistical Research Group, Columbia University, with EisenhartC.HastayM. W.WallisW. A. (Eds.), Selected techniques of statistical analysis. New York: McGraw-Hill, 1947. Pp. 395–416.
5.
FisherR. A.Statistical methods for research workers. (14th ed.) New York: Hafner, 1970.
6.
GarsideG. R.MackC.Actual type I error probabilities for various tests in the homogeneity case of the 2 × 2 contingency table. American Statistician, 1976, 30, 18–21.
7.
GrizzleJ. E.Continuity correction in the chi-square test for 2 × 2 tables. American Statistician, 1967, 21, 28–32.
8.
McDonaldL. L.DavidB. M.MillikenG. A.A nonrandomized unconditional test for comparing two proportions in 2 × 2 contingency tables. Technometrics, 1977, 19, 145–157.
9.
OverallJ. E.Continuity correction for Fisher's exact probability test. Journal of Educational Statistics, 1980, 5, 177–190.
