文章基本信息

标题：Using Stacking to Average Bayesian Predictive Distributions (with Discussion)
本地全文：下载
作者：Yuling Yao ; Aki Vehtari ; Daniel Simpson 等
期刊名称：Bayesian Analysis
印刷版ISSN：1931-6690
电子版ISSN：1936-0975
出版年度：2018
卷号：13
期号：3
页码：917-1007
DOI：10.1214/17-BA1091
语种：English
出版社：International Society for Bayesian Analysis
摘要：Bayesian model averaging is flawed in the M-open setting in which the true data-generating process is not one of the candidate models being fit. We take the idea of stacking from the point estimation literature and generalize to the combination of predictive distributions. We extend the utility function to any proper scoring rule and use Pareto smoothed importance sampling to efficiently compute the required leave-one-out posterior distributions. We compare stacking of predictive distributions to several alternatives: stacking of means, Bayesian model averaging (BMA), Pseudo-BMA, and a variant of Pseudo-BMA that is stabilized using the Bayesian bootstrap. Based on simulations and real-data applications, we recommend stacking of predictive distributions, with bootstrapped-Pseudo-BMA as an approximate alternative when computation cost is an issue.
关键词：Bayesian model averaging; model combination; proper scoring rule;predictive distribution; stacking; Stan.