You are not currently logged in.
Access JSTOR through your library or other institution:
An Effective Algorithm for the Noncentral Beta Distribution Function
Harry O. Posten
The American Statistician
Vol. 47, No. 2 (May, 1993), pp. 129-131
Stable URL: http://www.jstor.org/stable/2685195
Page Count: 3
You can always find the topics here!Topics: Distribution functions, Algorithms, Computational statistics, Truncation errors, Natural logarithms, Fortran
Were these topics helpful?See something inaccurate? Let us know!
Select the topics that are inaccurate.
Preview not available
A simple recursive algorithm is provided for evaluating the noncentral beta distribution function. This algorithm basically reduces the problem to that of evaluating a single central beta distribution function. The algorithm is summarized in a step-by-step form. Since the noncentral F distribution function can be evaluated directly from the noncentral beta distribution function, the algorithm has broad practical use for evaluating the power of analysis of variance and other F tests. The method of this algorithm was used in Lenth. The latter article, however, focuses on a FORTRAN program and on an error bound for the procedure. It does not provide a full development of the procedure. The present article provides a complete development enabling one to readily produce a noncentral beta distribution function program in any desired language, with understanding for each step.
The American Statistician © 1993 American Statistical Association