Mean estimate for Shewhart-chart-monitored processes subject to random shifts

The Shewhart control chart is a widely used statistical control tool that helps detect a possible process shift (out-of-control process). Though the Shewhart chart is in theory a monitoring tool that reveals only the result of a hypothesis testing. In practice chart´s signalling is often used as the evidence for making process adjustment. In this paper we develop a process mean estimator for processes monitored by Shewhart charts. This mean the estimate can serve as an important reference for investigating assignable causes and taking appropriate corrective actions. A semiconductor fabrication process is used as an example to illustrate the methodology