On predictive density estimation with additional information
Abstract
Based on independently distributed and , we consider the efficiency of various predictive density estimators for , with the additional information and known . We provide improvements on benchmark predictive densities such as plug-in, the maximum likelihood, and the minimum risk equivariant predictive densities. Dominance results are obtained for divergence losses and include Bayesian improvements for reverse Kullback-Leibler loss, and Kullback-Leibler (KL) loss in the univariate case (). An ensemble of techniques are exploited, including variance expansion (for KL loss), point estimation duality, and concave inequalities. Representations for Bayesian predictive densities, and in particular for associated with a uniform prior for truncated to , are established and are used for the Bayesian dominance findings. Finally and interestingly, these Bayesian predictive densities also relate to skew-normal distributions, as well as new forms of such distributions.
Cite
@article{arxiv.1709.07778,
title = {On predictive density estimation with additional information},
author = {Éric Marchand and Abdolnasser Sadeghkhani},
journal= {arXiv preprint arXiv:1709.07778},
year = {2017}
}
Comments
30 pages, 4 Figures