论文信息 - Conjugate Parameterizations for Natural Exponential Families

Conjugate Parameterizations for Natural Exponential Families

Abstract Recently, Consonni and Veronese have shown that the form of the standard conjugate distribution for the mean parameter μ of a univariate natural exponential family F coincides with that of the distribution induced on μ by the standard conjugate distribution for the canonical parameter if and only if F has a quadratic variance function. In this article we present significant extensions of this result, identifying conditions under which transformations of the canonical or mean parameter preserve the form of the standard conjugate family. Generalizations to the multivariate case are also considered, and results relating Jeffreys's prior to the standard conjugate family are presented. The variance function is seen to play an important role throughout.

Adrian F. M. Smith | E. Gutiérrez-Peña

[1] H. Jeffreys,et al. Theory of probability , 1896 .

[2] P. Diaconis,et al. Conjugate Priors for Exponential Families , 1979 .

[3] J. F. C. Kingman,et al. Information and Exponential Families in Statistical Theory , 1980 .

[4] C. Morris. Natural Exponential Families with Quadratic Variance Functions , 1982 .

[5] J. Magnus,et al. Matrix Differential Calculus with Applications in Statistics and Econometrics (Revised Edition) , 1999 .

[6] Gérard Letac,et al. Natural Real Exponential Families with Cubic Variance Functions , 1990 .

[7] M. Casalis,et al. Les familles exponentielles à variance quadratique homogène sont des lois de Wishart sur un cône symétrique , 1991 .

[8] Guido Consonni,et al. Conjugate Priors for Exponential Families Having Quadratic Variance Functions , 1992 .

[9] J. Q. Smith,et al. 1. Bayesian Statistics 4 , 1993 .

[10] LES 2N + 4 TYPES DE FAMILLES EXPONENTIELLES NATURELLES SUR RN A FONCTION-VARIANCE QUADRATIQUE SIMPLE , 1994 .

[11] The $2d+4$ simple quadratic natural exponential families on ${\bf R}\sp d$ , 1996 .