An independence property for the product of GIG and gamma laws. (English) Zbl 1010.62010

Summary: H. Matsumoto and M. Yor [ Nagoya Math. J. 162, 65-86 (2001; Zbl 0983.60075)] have recently discovered an interesting transformation which preserves a bivariate probability measure which is a product of the generalized inverse Gaussian (GIG) and gamma distributions. This paper is devoted to a detailed study of this phenomenon.
Let \(X\) and \(Y\) be two independent, positive random variables. We prove that \(U=(X+Y)^{-1}\) and \(V=X^{-1}-(X+Y)^{-1}\) are independent if and only if there exist \(p,a,b>0\) such that \(Y\) is gamma distributed with shape parameter \(p\) and scale parameter \(2a^{-1}\), and such that \(X\) has a GIG distribution with parameters \(-p, a\) and \(b\) (the direct part for \(a=b\) was obtained by Matsumoto and Yor). The result is partially extended to the case where \(X\) and \(Y\) take values in the cone \(V_+\) of symmetric positive definite \(r\times r\) real matrices as follows:
Under the hypothesis of smoothness of densities, we prove that \(U=(X+Y)^{-1}\) and \(V=X^{-1}-(X+Y)^{-1}\) are independent if and only if there exist \(p>(r-1)/2\) and \(a\) and \(b\) in \(V_+\) such that \(Y\) is Wishart distributed with shape parameter \(p\) and scale parameter \(2a^{-1}\), and such that \(X\) has a matrix GIG distribution with parameters \(-p, a\) and \(b\). The direct result is also extended to singular Wishart distributions.


62E10 Characterization and structure theory of statistical distributions
62H05 Characterization and structure theory for multivariate probability distributions; copulas
60E05 Probability distributions: general theory


Zbl 0983.60075
Full Text: DOI


[1] Bernadac, E. (1995). Random continued fractions and inverse Gaussian distribution on a symmetric cone. J. Theoret. Probab. 8 221-260. · Zbl 0820.60008
[2] Butler, R. W. (1998). Generalized inverse Gaussian distributions and their Wishart connexions. Scand. J. Statist. 25 69-75. · Zbl 0909.60022
[3] Casalis, M. and Letac, G. (1996). The Lukacs-Olkin-Rubin characterization of the Wishart distributions on the symmetric cones. Ann. Statist. 24 763-784. · Zbl 0906.62053
[4] Faraut, J. and Koranyi, A. (1994). Analysis on Symmetric Cones. Oxford Univ. Press. · Zbl 0841.43002
[5] Herz, C. S. (1955). Bessel functions of matrix argument. Ann. of Math. 61 474-523. JSTOR: · Zbl 0066.32002
[6] Letac, G. and Massam, H. (1998). Quadratic and inverse regressions for Wishart distributions. Ann. Statist. 26 573-595. · Zbl 1073.62536
[7] Letac, G. and Seshadri, V. (1983). A characterization of the generalized inverse Gaussian distribution by continued fractions.Wahrsch. Verw. Gebiete 62 485-489. · Zbl 0488.60020
[8] Lukacs, E. (1955). A characterization of the gamma distribution. Ann. Math. Statist. 26 319-324. · Zbl 0065.11103
[9] Massam, H. (1994). An exact decomposition theorem and a unified view of some related distributions for a class of exponential transformation models on symmetric cones. Ann. Statist. 22 369-394. · Zbl 0811.62023
[10] Matsumoto, H. and Yor, M. (1998). An analogue of Pitman’s 2M X theorem for exponential Wiener functional, Part II: the role of the generalized inverse Gaussian laws. Nagoya Math. J. · Zbl 0983.60075
[11] Muirhead, R. J. (1982). Aspects of Multivariate Statistical Theory. Wiley, New York. · Zbl 0556.62028
[12] Olkin, I. and Rubin, H. (1962). A characterization of the Wishart distribution. Ann. Math. Statist. 33 1272-1280. · Zbl 0111.34202
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.