The power law process has proved to be a useful tool in characterizing the failure process of repairable systems. This paper presents a procedure for detecting and estimating a mixture of reliable and unreliable (defective) systems. The test of a mixture, based on a simple likelihood ratio, is illustrated with truncated failure data for copy machines. Bootstrap methods are used to gauge the estimation uncertainty, and optimal decisions for system replacement are determined based on the observed likelihood.

Document Type


Publication Date


Publisher Statement

Copyright © 2007 American Society for Quality. This article first appeared in Journal of Quality Technology 39, no. 2 (April 2007): 140-150.

Please note that downloads of the article are for private/personal use only.