Enhancing reliability analysis via adaptive progressively type-II censored data utilizing the inverse Weibull Model and binomial removal patterns

Abstract Analyzing reliability using complete data is often impractical due to the long lifetimes of modern products and the associated time and resource constraints of data collection. Consequently, censored data are commonly employed in reliability analysis. This study focuses on reliability estimation for the inverse Weibull distribution under an adaptive progressive Type-II censoring scheme with binomial removals, which allows the number of removed units at each stage to vary randomly and provides greater flexibility in modeling realistic life-testing experiments. The novelty of this work lies in incorporating binomial removal mechanisms into the adaptive censoring framework and developing comprehensive classical and Bayesian inference procedures for both the model parameters and associated reliability measures. Classical estimation is carried out using maximum likelihood methods to obtain point estimates and approximate confidence intervals, while Bayesian estimation is performed using Markov Chain Monte Carlo techniques to derive Bayes estimates and credible intervals. A detailed simulation study is conducted to evaluate the performance of the proposed estimation methods under various experimental settings. The results demonstrate the effectiveness and practical applicability of the proposed approach for reliability estimation of the inverse Weibull model.