Abstract

Reliability improvement is a primary goal of product life data analysis. Achieving that goal requires understanding how and why products fail. Most products are subject to multiple failure mechanisms. A household refrigerator, for example, may fail because of a compressor malfunction, a thermostat defect or a failure of the electronic control board. These distinct causes are referred to commonly as competing failure modes or competing risks. Because different failure modes often arise from different physical mechanisms, analyzing them separately can provide insights that are not available from an overall analysis of all failures combined.