Unfortunately many of the numerous algorithms for computing the comulative distribution function (cdf) and noncentrality parameter of the noncentral F and beta distributions can produce completely incorrect results as demonstrated in the paper by examples. Existing algorithms are scrutinized and those parts that involve numerical difficulties are identified. As a result, a pseudo code is presented in which all the known numerical problems are resolved. This pseudo code can be easily implemented in programming language C or FORTRAN without understanding the complicated mathematical background.
Symbolic evaluation of a finite and closed formula is proposed to compute exact cdf values. This approach makes it possible to check quickly and reliably the values returned by professional statistical packages over an extraordinarily wide parameter range without any programming knowledge.
This research was motivated by the fact that a very useful table for calculating the size of detectable effects for ANOVA tables contains suspect values in the region of large noncentrality parameter values compared to the values obtained by Patnaik’s 2-moment central-F approximation. The cause is identified and the corrected form of the table for ANOVA purposes is given. The accuracy of the approximations to the noncentral-F distribution is also discussed.
Benton, D., Krishnamoorthy, K.: Computing discrete mixtures of continuous distributions: noncentral chisquare, noncentral t and the distribution of the square of the sample multiple correlation coefficient. Comput. Stat. Data Anal. 43, 249–267 (2003)
Posten, H.O.: An effective algorithm for the noncentral beta distribution function. Am. Stat. 47, 129–131 (1993)
Severo, N., Zelen, M.: Normal approximation to the chi-square and noncentral F probability functions. Biometrika 47, 411–416 (1960)
Sibuya, M.: On the noncentral beta distribution function (1967). Unpublished manuscript. The equation can be found in the book of Johnson, Kotz, and Balakrishnan (1995), p. 485 (30.12)
Singh, K.P., Relyea, G.E.: Computation of noncentral F probabilities. A computer program. Comput. Stat. Data Anal. 13, 95–102 (1992). The misprint on p. 97 was corrected by Chattamvelli (1995)
Tiku, M.L.: A note on approximating to the noncentral F distribution. Biometrika 53, 606–610 (1966)
Tiwari, R.C., Yang, J.: Algorithm AS 318: An efficient recursive algorithm for computing the distribution function and non-centrality parameter of the non-central F-distribution. Appl. Stat. 46, 408–413 (1997)
Wang, M.C., Kennedy, W.J.: A self-validating numerical method for computation of central and non-central F probabilities and percentiles. Stat. Comput. 5, 155–163 (1995)