A robust bootstrap confidence interval for the two-parameter Weibull distribution based on the method of trimmed moments

Since the Weibull distribution plays a central role in life testing and reliability theory, and the confidence intervals of their parameters are heavily affected by outliers and censoring in real reliability data, a robust bootstrap confidence interval for the two-parameter Weibull distribution based on the method of trimmed moments is proposed in this paper, where the method of trimmed moments (MTM) is utilized instead of the maximum likelihood estimator (MLE) in the Bootstrap confidence interval construction. The robustness of the proposed method is shown and compared with that of the MLE method by Monte Carlo simulations, and some conclusions are given in the end for applications.