Loading...
An assessment of prior choices in a hierarchical Bayesian model for failure data
Garcia, Jovanni Gwyn, Richard Schreck, Elliott Dail, Alexander
Garcia, Jovanni
Gwyn, Richard
Schreck, Elliott
Dail, Alexander
Citations
Altmetric:
Files
Loading...
JovanniGarciaPoster.pdf
Adobe PDF, 597.15 KB
Loading...
JGarciaAbstract.pdf
Adobe PDF, 76.83 KB
Other Names
Location
Time Period
Advisors
Original Date
Digitization Date
Issue Date
2025
Type
Abstract
Poster
Poster
Genre
Keywords
Hierarchical Bayesian modeling,Bayesian inference,Reliability analysis
Subjects (LCSH)
Citation
Garcia, J., Gwyn, R., Schreck, E., Dail, A., & Dao, M. An assessment of prior choices in a hierarchical Bayesian model for failure data. -- FYRE in STEM Showcase, 2025.
Abstract
In recent decades, reliability analysis has become increasingly important for risk assessment and management in industrial system control. Traditional statistical methods may fall short when the failure data is limited. Meanwhile, Bayesian inference offers a strong alternative by enabling the integration of prior knowledge, expert judgment, and historical data from similar systems to improve failure modeling and estimation. The hierarchical Bayesian modeling (HBM) framework explores how prior choices influence failure predictions. A beta-binomial likelihood is coupled with five distinct prior distributions to characterize the behavior of the industrial component in three data scenarios of varying sample sizes, reflecting real-world uncertainty and variability. The results demonstrate that in the presence of limited data, the prior selection significantly impacts posterior predictions, showing the sensitivity of Bayesian models to prior assumptions. The importance of careful prior selection to improve reliability estimates and support maintenance engineers in making more informed decisions under different process uncertainty.
Table of Contents
Description
Poster and abstract presented at the FYRE in STEM Showcase, 2025.
Research project completed at the Department of Mathematics, Statistics and Physics.
Research project completed at the Department of Mathematics, Statistics and Physics.
Publisher
Wichita State University
Journal
Book Title
Series
FYRE in STEM 2025