Work

Parametric Estimation in Censored Life-Testing: A Bayesian MAP Approach for Exponential and Weibull Distributions

Year: 2026
Type: article
Abstract: This study evaluates the finite-sample performance of maximum likelihood estimation (MLE) and Bayesian maximum a posteriori (MAP) estimation for Exponential and Weibull lifetime distributions under Type-II right censoring. Data were simulated from both distributions, with each life-testing experiment ending after a specified number of failures among n units. Estimator performance was assessed using bias, mean squared error (MSE), root mean squared error (RMSE) and mean absolute error (MAE) under alternative prior specifications, including calibrated, weakly informative and deliberately misspecified priors. The results indicate that the relative performance of MAP and MLE depends on the quality of prior information and the degree of censoring. For the Weibull distribution, estimation performance also differed between the shape and scale parameters. An illustrative application to ball-bearing fatigue-life observations using their original right-censoring information further demonstrates posterior-mode estimation, prior sensitivity and Markov Chain Monte Carlo (MCMC) based uncertainty quantification. In summary, the location of the MAP estimate within the region of greatest posterior concentration is consistent with direct numerical maximisation of the joint posterior density.
Source: Symmetry
Language: English
Open Access status: gold
Estimated APC paid: $2,896
OpenAlex ID: W7225914945
FWCI:
Cites: 33
Cited by:
Related to: 10