Multiple-testing control charts for correlated mixed-type quality variables
摘要
Quality control applications in the modern era, especially for non-manufacturing processes, often involve having to monitor correlated variables of different types, continuous, count, and categorical. Most of the multivariate control charts in the existing literature implicitly assume that the correlated variables to be monitored are of the same type. Another equally challenging task in multivariate quality control that has received relatively little attention is identifying parameters that are actually out of control (OC), when an OC signal is detected on a control chart. In this study, we develop a Shewhart-type multiple control chart based on the step-up multiple testing procedure. The proposed chart is shown to have similar overall performance as compared to the existing charts in terms of detecting OC process. Furthermore, in terms of the diagnostic capability, which is defined as the effectiveness of a charting mechanism in accurately identifying the true OC parameters once a signal is triggered, the proposed chart has a better overall performance.