๐”– Bobbio Scriptorium
โœฆ   LIBER   โœฆ

Posterior variance for quadratic natural exponential families

โœ Scribed by Denys Pommeret

Publisher
Elsevier Science
Year
2001
Tongue
English
Weight
93 KB
Volume
53
Category
Article
ISSN
0167-7152

No coin nor oath required. For personal study only.

โœฆ Synopsis

Within the framework of the quadratic natural exponential families we construct a basis of polynomials orthogonal with respect to the posterior density. This construction is adapted from Walter and Hamedani (Ann. Statist. 3 (1991) 1191) and we exploit them to establish lower bounds for the posterior variance.

๐Ÿ“œ SIMILAR VOLUMES

A property of natural exponential famili
A property of natural exponential families in Rn with simple quadratic variance functions
โœ V. Seshadri ๐Ÿ“‚ Article ๐Ÿ“… 1997 ๐Ÿ› Elsevier Science ๐ŸŒ English โš– 386 KB

A generalization to N" of a property of natural exponential families on ~ with simple quadratic variances is obtained. This property yields the original density in terms of the Laplace transform of the conjugate prior for the natural parameter.

A reverse martingale property that chara
A reverse martingale property that characterizes the natural exponential family with quadratic variance function
โœ Fernando Lรณpez-Blรกzquez; Begoรฑa Salamanca-Miรฑo ๐Ÿ“‚ Article ๐Ÿ“… 2000 ๐Ÿ› Elsevier Science ๐ŸŒ English โš– 90 KB

We give a characterization of the natural exponential family with quadratic variance function in terms of a discrete-time reverse martingale-like property. The proof of this result is based on the properties of the set of UMVU estimable functions.

Asymptotic Normality of Posterior Distri
Asymptotic Normality of Posterior Distributions for Exponential Families when the Number of Parameters Tends to Infinity
โœ Subhashis Ghosal ๐Ÿ“‚ Article ๐Ÿ“… 2000 ๐Ÿ› Elsevier Science ๐ŸŒ English โš– 172 KB

We study consistency and asymptotic normality of posterior distributions of the natural parameter for an exponential family when the dimension of the parameter grows with the sample size. Under certain growth restrictions on the dimension, we show that the posterior distributions concentrate in neig