On predictive density estimation with additional information

DOI10.1214/18-EJS1493MaRDI QIDQ1711575zbMATH OpenOpenAlexWikidataFDO

Authors Éric Marchand, Abdolnasser Sadeghkhani

Publication date 18 January 2019

Published in Electronic Journal of Statistics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1709.07778, https://projecteuclid.org/euclid.ejs/1544842900

zbMATH Keywords

skew-normaladditional informationdualitymultivariate normaldominancepredictive densityplug-inBayes estimatorsrestricted parameterKullback-Leibler lossfrequentist riskvariance expansion\(\alpha\)-divergence loss

Mathematics Subject Classification ID

Bayesian inference (62F15) Estimation in multivariate analysis (62H12) Inference from stochastic processes and prediction (62M20)

Abstract: Based on independently distributed $X_{1}sim{N}_p(het{a}_1,sigm{a}_1^2{I}_p)$ and $X_{2}sim{N}_p(het{a}_2,sigm{a}_2^2{I}_p)$, we consider the efficiency of various predictive density estimators for $Y_{1}sim{N}_p(het{a}_1,sigm{a}_Y^2{I}_p)$, with the additional information $het{a}_1-het{a}_{2}inA$ and known $sigm{a}_1^2,sigm{a}_2^2,sigm{a}_Y^2$. 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 $alpha-$divergence losses and include Bayesian improvements for reverse Kullback-Leibler loss, and Kullback-Leibler (KL) loss in the univariate case ($p=1$). 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 $hat{q}_{p{i}_{U,A}}$ associated with a uniform prior for $heta=(het{a}_1,het{a}_2)$ truncated to $hetainmathbb{R}^{2p}:het{a}_1-het{a}_{2}inA$, 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.

Recommendations

• On predictive density estimation under \(\alpha\)-divergence loss
• On improved predictive density estimation with parametric constraints
• On efficient prediction and predictive density estimation for normal and spherically symmetric models
• Improved minimax predictive densities under Kullback-Leibler loss
• PREDICTIVE DENSITY ESTIMATION FOR MULTIPLE REGRESSION

Cites work

• scientific article; zbMATH DE number 3930122 (Why is no real title available?)
• scientific article; zbMATH DE number 44577 (Why is no real title available?)
• scientific article; zbMATH DE number 3513162 (Why is no real title available?)
• scientific article; zbMATH DE number 854963 (Why is no real title available?)
• scientific article; zbMATH DE number 3252891 (Why is no real title available?)
• A Bayesian interpretation of the multivariate skew-normal distribution.
• A Generalized Bayes Rule for Prediction
• A shrinkage predictive distribution for multivariate normal observables
• A unified view on skewed distributions arising from selections
• Admissible predictive density estimation
• Bayesian inference on order-constrained parameters in generalized linear models
• Bayesian predictive densities for linear regression models under α -divergence loss: Some results and open problems
• Combining sample information in estimating ordered normal means
• Confidence interval estimation subject to order restrictions
• Confidence intervals under order restrictions
• Constrained Statistical Inference
• Estimating one of two normal means when their difference is bounded
• Estimation in restricted parameter spaces: a review
• Estimation of the Larger Translation Parameter
• Estimation of the Last Mean of a Monotone Sequence
• Estimation of the mean of a multivariate normal distribution
• Estimation, prediction and the Stein phenomenon under divergence loss
• Generalized skew normal model
• Goodness of prediction fit
• Improved minimax predictive densities under Kullback-Leibler loss
• Improved prediction for a multivariate normal distribution with unknown mean and variance
• Improving on the MLE of a bounded normal mean.
• Inadmissible estimators of normal quantiles and two-sample problems with additional information
• Intrinsic losses
• Minimax estimation of a bounded normal mean vector
• Minimax estimation of location parameters for spherically symmetric distributions with concave loss
• Modified Bessel functions and their applications in probability and statistics
• On Bayes estimators with uniform priors on spheres and their comparative performance with maximum likelihood estimators for estimating bounded multivariate normal means
• On estimating a bounded normal mean with applications to predictive density estimation
• On improved predictive density estimation with parametric constraints
• On predictive density estimation for location families under integrated absolute error loss
• On predictive density estimation for location families under integrated squared error loss
• Restricted parameter space estimation problems. Admissibility and minimaxity properties.
• Skewed multivariate models related to hidden truncation and/or selective reporting. With discussion and a rejoinder by the authors.
• The nontruncated marginal of a truncated bivariate normal distribution
• The quadratic loss of isotonic regression under normality
• The reflected normal loss function
• Uniform priors on convex sets improve risk

Cited in

(10)

• scientific article; zbMATH DE number 1833969 (Why is no real title available?)
• Predicting the scoring time in hockey
• Bayesian predictive densities based on latent information priors
• On Bayesian estimation of densities and sampling distributions: The posterior predictive distribution as the Bayes estimator
• On predictive density estimation under \(\alpha\)-divergence loss
• On improved predictive density estimation with parametric constraints
• Matrix variate density estimation with additional information
• Bayesian predictive density estimation for a chi-squared model using information from a normal observation with unknown mean and variance
• Bayesian inference and prediction for mean-mixtures of normal distributions
• On efficient prediction and predictive density estimation for normal and spherically symmetric models

This page was built for publication: On predictive density estimation with additional information

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1711575)