BayesESS: A Tool for Quantifying the Impact of Parametric Priors in Bayesian Analysis

Authors

Jaejoon Song
Satoshi Morita
Ying-Wei Kuo
J Jack Lee

Publication Date

5-1-2023

Journal

SoftwareX

DOI

10.1016/j.softx.2023.101358

PMID

37377886

PMCID

PMC10299797

PubMedCentral® Posted Date

June 2023

PubMedCentral® Full Text Version

Author MSS

Abstract

Bayesian inference has become an attractive choice for scientists seeking to incorporate prior knowledge into their modeling framework. While the R community has been an important contributor in facilitating Bayesian statistical analyses, software to evaluate the impact of prior knowledge to such modeling framework has been lacking. In this article, we present BayesESS, a comprehensive, free, and open source R package for quantifying the impact of parametric priors in Bayesian analysis. We also introduce an accompanying web-based application for estimating and visualizing Bayesian effective sample size for purposes of conducting or planning Bayesian analyses.

Keywords

Bayesian analysis, Effective sample size, Posterior distribution, R package

Published Open-Access

yes

Recommended Citation

Song, Jaejoon; Morita, Satoshi; Kuo, Ying-Wei; et al., "BayesESS: A Tool for Quantifying the Impact of Parametric Priors in Bayesian Analysis" (2023). Faculty, Staff and Student Publications. 1426.
https://digitalcommons.library.tmc.edu/uthgsbs_docs/1426