Resumen de Detection and Estimation of a Mixture in Power Law Processes for a Repairable System
Ni Wang, Paul Kvam, Jye-Chyi Lu
The power law process has been shown to be a useful tool in characterizing the failure process of repairable systems. In this study, a procedure is proposed for detecting and estimating a mixture of reliable and unreliable systems. Using a simple likelihood ratio, a test of a mixture for copy machines is illustrated with truncated failure data. The estimation uncertainty is determined with bootstrap methods. Optimal decisions for system replacement are determined based on the observed likelihood.
