|
Activity Number:
|
340
- SPEED: Bayesian Methods, Part 1
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, July 30, 2019 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Section on Bayesian Statistical Science
|
|
Abstract #306436
|
|
|
Title:
|
Predictive Density Estimation of Multivariate Skew-Normal Distribution
|
|
Author(s):
|
Othmane Kortbi*
|
|
Companies:
|
UAE University Al-Ain
|
|
Keywords:
|
Predictive density;
Skew-normal distribution;
Kullback–Leibler loss;
Bayes estimator;
Minimum risk equivariant;
Dominance
|
|
Abstract:
|
This work studies decision theoretic properties of predictive density estimators for multivariate skew-normal distribution with known skewness parameters under Kullback-Leibler loss. We investigated the properties of the benchmark estimator which is the the minimum risk equivariant predictive density estimator. A wide class of plug-in estimators improving on the best equivariant estimator is constructed when the dimension of the location parameters is larger than or equal to four. A class of Bayes estimators is also considered and their dominance property studied. The performances of these estimators are investigated by simulation.
|
Authors who are presenting talks have a * after their name.
