Efficiency of Linear Bayes Rules for a Normal Mean-Skewed Priors Class

Saurabh Mukhopadhyay, Brani Vidakovic
Duke University

Nov 10 1993

In this paper we explore the performance of linear Bayes rules in estimating a normal mean. We take a robust Bayesian standpoint, expressing our limited information about the parameter by adopting a family T of priors. The family of priors we are using if fully described in Azzalini (1983), and is suitable for modeling non-symmetric situations. We find in many cases that the linear Bayes rules have reasonably high efficiencies (with respect to the corresponding Bayes rules), and therefore, can be used instead of the Bayes rules as the linear rules are much easier to obtain.


Skewed family of priors, Robust Bayesian analysis, Linear Bayes rules, Efficiency


PDF icon 1993-24.pdf