Simulation-efficient shortest probability intervals

DOI10.1007/S11222-015-9563-8zbMATH Open1331.62154arXiv1302.2142OpenAlexW1865208146MaRDI QIDQ5963782FDOQ5963782

Authors: Tian Zheng, Andrew Gelman, Ying Liu 

Publication date: 23 February 2016

Published in: Statistics and Computing (Search for Journal in Brave)

Abstract: Bayesian highest posterior density (HPD) intervals can be estimated directly from simulations via empirical shortest intervals. Unfortunately, these can be noisy (that is, have a high Monte Carlo error). We derive an optimal weighting strategy using bootstrap and quadratic programming to obtain a more compu- tationally stable HPD, or in general, shortest probability interval (Spin). We prove the consistency of our method. Simulation studies on a range of theoret- ical and real-data examples, some with symmetric and some with asymmetric posterior densities, show that intervals constructed using Spin have better cov- erage (relative to the posterior distribution) and lower Monte Carlo error than empirical shortest intervals. We implement the new method in an R package (SPIn) so it can be routinely used in post-processing of Bayesian simulations.

Full work available at URL: https://arxiv.org/abs/1302.2142

Recommendations

• Efficiently Simulating the Coverage Properties of Interval Estimates
• A Note on the Construction of Highest Posterior Density Intervals
• scientific article; zbMATH DE number 5005874
• Estimating Bayesian credible intervals
• Highest posterior mass prediction intervals for binomial and Poisson distributions

zbMATH Keywords

bootstrapBayesian computationhighest posterior density

Mathematics Subject Classification ID

Bayesian inference (62F15)

Cites Work

• Asymptotic Statistics
• Bootstrap methods: another look at the jackknife
• Title not available (Why is that?)
• Title not available (Why is that?)
• How Many People Do You Know in Prison?
• Order Statistics
• Inference from simulations and monitoring convergence

Cited In (5)

• A Note on the Construction of Highest Posterior Density Intervals
• Computing highest density regions for continuous univariate distributions with known probability functions
• Efficiently Simulating the Coverage Properties of Interval Estimates
• Markov-modulated Hawkes processes for modeling sporadic and bursty event occurrences in social interactions
• Posterior distribution of nondifferentiable functions

Uses Software

• R
• SPIN
• BUGS
• BayesDA
• RStan

This page was built for publication: Simulation-efficient shortest probability intervals

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5963782)