Bayesian D-optimal Designs for Weibull Distribution with Censoring

Bayesian optimal designs have received increasing attention in recent years, especially in reliability experiments. Weibull distribution is one of the most widely used in reliability analysis, owing to its various shapes for the probability density function and its convenient representation of lifetime data, particularly when data are censored, which is quite common in most life‐testing experiments. This paper provides analytical characterizations of Bayesian D‐optimal designs for Weibull distribution, as well as proposes an algorithm for finding a Bayesian D‐optimal design that combines the point exchange algorithm with the Monte Carlo simulation method. Different censoring mechanisms are incorporated, and the robustness of designs against parameters' mis‐specification is assessed.