A simple FORTRAN program is provided for calculating the power of statistical tests based on the chi-square distribution. The program produces reasonably accurate approximations to the exact probabilities obtained from the noncentral chi-square distribution. The calculation of the noncentrality parameter is also discussed for tests of independence and goodness-of-fit.
Get full access to this article
View all access options for this article.
References
1.
Bishop, Y. M., Fienberg, S., and Holland, P.Discrete multivariate analysis. Cambridge, Mass.: MIT Press, 1975.
2.
Cohen, J.Statistical power analysis for the behavioral sciences (Rev. ed. New York: Academic Press, 1977.
3.
Dudewicz, E. J.Introduction to statistics and probability. New York: Holt , Rinehart, and Winston , 1976.
4.
Fienberg, S.The analysis of cross-classified categorical data. Cambridge, Mass.: MIT Press, 1977.
5.
Hastings, C.Approximations for digital computers . Princeton, New Jersey: Princeton University Press, 1955.
6.
Laubscher, N. F.Normalizing the noncentral t and F distributions. Annals of Mathematical Statistics , 1960, 31, 1105-1112.
7.
Patnaik, P. B.The non-central chi-square and F-distributions and their applications. Biometrika , 1949, 36, 203-232.
8.
Severo, N. C. and Zelen, M.Normal approximation to the chi-square and non-central F probability functions. Biometrika, 1960 , 47, 411-416.
9.
Woodward, J. A. and Overall, J. E.A computer program for calculating power of the F-test. EDUCATIONAL AND PSYCHOLOGICAL MEASUREMENT , 1976, 36, 165-168.
