Abstract
Whenever one designs a control chart procedure, the proper choice of a sampling interval must reflect the expected time the process is in control before an assignable cause occurs and produces a change in the process. Yet, the expected time in control usually will change over the life of the process. This paper proposes that the proper choice of a sampling interval may be viewed within the context of a multi-level sampling plan. Thus, the sampling interval can be changed to reflect the current state of the process. In so doing, one can maintain the desired statistical properties of the control chart while simultaneously considering the sampling costs involved.
Additional information
Notes on contributors
G. Geoffrey Vining
Dr. Vining is an Associate Professor in the Department of Statistics. He is a Senior member of ASQ.
Marion R. Reynolds
Dr. Reynolds is a Professor in the Departments of Statistics and Forestry. He is a Member of ASQ.