Uncertainty Analysis of Weibull Estimators for Interval-Censored Data

The two-parameter Weibull is one of the most popular statistical distributions used to describe the reliability and time-to-failure characteristics of mechanical systems. This paper deals with a Monte Carlo approach to quantify two major sources of uncertainty in Weibull analysis that are commonly found in industrial applications - parameter error introduced due to extended inspection intervals, and error due to different estimation algorithms for interval-censored data. The objective of this paper is to describe some of the numerical methods and processes used to estimate interval-censored Weibull parameters and estimate their bias for a typical industrial application.