skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Accommodating Uncertainty in Prior Distributions

Abstract

A fundamental premise of Bayesian methodology is that a priori information is accurately summarized by a single, precisely de ned prior distribution. In many cases, especially involving informative priors, this premise is false, and the (mis)application of Bayes methods produces posterior quantities whose apparent precisions are highly misleading. We examine the implications of uncertainty in prior distributions, and present graphical methods for dealing with them.

Authors:
 [1];  [1]
  1. Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
Publication Date:
Research Org.:
Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
Sponsoring Org.:
USDOE National Nuclear Security Administration (NNSA)
OSTI Identifier:
1340952
Report Number(s):
LA-UR-17-20370
DOE Contract Number:  
AC52-06NA25396
Resource Type:
Technical Report
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICS AND COMPUTING; Bayesian sensitivity analysis; imprecise probabilities; informative priors

Citation Formats

Picard, Richard Roy, and Vander Wiel, Scott Alan. Accommodating Uncertainty in Prior Distributions. United States: N. p., 2017. Web. doi:10.2172/1340952.
Picard, Richard Roy, & Vander Wiel, Scott Alan. Accommodating Uncertainty in Prior Distributions. United States. doi:10.2172/1340952.
Picard, Richard Roy, and Vander Wiel, Scott Alan. Thu . "Accommodating Uncertainty in Prior Distributions". United States. doi:10.2172/1340952. https://www.osti.gov/servlets/purl/1340952.
@article{osti_1340952,
title = {Accommodating Uncertainty in Prior Distributions},
author = {Picard, Richard Roy and Vander Wiel, Scott Alan},
abstractNote = {A fundamental premise of Bayesian methodology is that a priori information is accurately summarized by a single, precisely de ned prior distribution. In many cases, especially involving informative priors, this premise is false, and the (mis)application of Bayes methods produces posterior quantities whose apparent precisions are highly misleading. We examine the implications of uncertainty in prior distributions, and present graphical methods for dealing with them.},
doi = {10.2172/1340952},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Thu Jan 19 00:00:00 EST 2017},
month = {Thu Jan 19 00:00:00 EST 2017}
}

Technical Report:

Save / Share: