# asa226

asa226, a MATLAB code which evaluates the cumulative distribution function (CDF) of the noncentral Beta Distribution, by Russell Lenth.

This is a version of Applied Statistics Algorithm 226.

The program can produce reasonably accurate answers for values of the noncentrality parameter up to about 100.

Note that an improvement to ASA226 was suggested by Frick, and implemented in the online copy available through STATLIB. When I run the improved copy, the computation fails. Therefore, the version I have put together has suppressed the improvement for now until I can determine the stray minus sign or logic error causing the problem.

### Licensing:

The computer code and data files described and made available on this web page are distributed under the MIT license

### Languages:

asa226 is available in a C version and a C++ version and a FORTRAN90 version and a MATLAB version

### Related Data and Programs:

asa063, a MATLAB code which evaluates the incomplete Beta function.

asa109, a MATLAB code which inverts the incomplete Beta function.

asa310, a MATLAB code which computes the CDF of the noncentral Beta distribution.

beta_nc, a MATLAB code which evaluates the CDF of the noncentral Beta distribution.

prob, a MATLAB code which evaluates and inverts a number of probabilistic distributions.

test_values, a MATLAB code which contains sample values for a number of distributions.

Ttoms179, a MATLAB code which evaluates the incomplete Beta function.

### Author:

Original FORTRAN77 version by Russell Lenth; Matlab version by John Burkardt.

### Reference:

1. H Frick,
Algorithm AS R84: A Remark on Algorithm AS 226: Computing Noncentral Beta Probabilities,
Applied Statistics,
Volume 39, Number 2, 1990, pages 311-312.
2. Russell Lenth,
Algorithm AS 226: Computing Noncentral Beta Probabilities,
Applied Statistics,
Volume 36, Number 2, 1987, pages 241-244.

### Source Code:

• betain.m computes the incomplete Beta function ratio.
• betanc.m computes the tail of the noncentral Beta distribution.

Last revised on 26 November 2018.