Laplace approximations to hypergeometric functions of two matrix arguments
We present a unified approach to Laplace approximation of hypergeometric functions with two matrix arguments. The general form of the approximation is designed to exploit the Laplace approximations to hypergeometric functions of a single matrix argument presented in Butler and Wood (Ann. Statist. 30 (2002) 1155, Laplace approximations to Bessel functions of matrix argument, J. Comput. Appl. Math. 155 (2003) 359) which have proved to be very accurate in a variety of settings. All but one of the approximations presented here appear to be new. Numerical accuracy is investigated in a number of statistical applications.
Year of publication: |
2005
|
---|---|
Authors: | Butler, Ronald W. ; Wood, Andrew T.A. |
Published in: |
Journal of Multivariate Analysis. - Elsevier, ISSN 0047-259X. - Vol. 94.2005, 1, p. 1-18
|
Publisher: |
Elsevier |
Keywords: | Asymptotic approximation Eigenvalue distribution Matrix-argument hypergeometric function Laplace approximation |
Saved in:
Online Resource
Saved in favorites
Similar items by person
-
Saddlepoint Approximations to the CDF of Some Statistics With Nonnormal Limit Distributions
Wood, Andrew T.A., (1993)
-
Improved Pivotal Methods for Constructing Confidence Regions With Directional Data
Fisher, Nicholas I., (1996)
-
On the derivatives of the normalising constant of the Bingham distribution
Kume, A., (2007)
- More ...