A Stochastic Expectation-Maximization Algorithm for the Analysis of System Lifetime Data with Known Signature

• Activity Number: 266
• Type: Contributed
• Date/Time: Monday, August 10, 2015 : 2:00 PM to 3:50 PM
• Sponsor: Quality and Productivity Section
• Author(s): Yandan Yang* and Hon Keung Tony Ng and Narayanaswamy Balakrishnan
• Companies: Southern Methodist University and Southern Methodist University and McMaster University
• Keywords: Expectation-Maximization algorithm ; Maximum likelihood estimation ; Monte Carlo Simulation ; Reliability data ; Type-II censoring

Abstract

Statistical estimation of the model parameters of component lifetime distribution based on system lifetime data with known system structure is discussed here. We propose the use of stochastic expectation-maximization (SEM) algorithm to obtain the maximum likelihood estimates of parameters based on complete and censored system lifetimes. Different ways to implement the SEM algorithm are also studied. We have shown that the proposed methods are feasible and easy to implement for various families of component lifetime distributions. The methodologies are then illustrated with two popular lifetime models -- the Weibull and Birnbaum-Saunders distributions. Monte Carlo simulation is used to compare the performance of the proposed methods with the corresponding estimation by direct maximization. An illustrative example is finally presented with some concluding remarks.