An improved exponentially weighted moving average chart for monitoring proportions using maxima nomination sampling

Abstract

We develop a new proportion control chart using the exponentially weighted moving average (EWMA) for the maxima nomination sampling (MNS) method. By using average run length (ARL), we compare it with conventional Shewhart and EWMA control charts based on the simple random sampling (SRS) method. We study the effect of the sample size, the set size, the in-control and out-of-control non-conforming proportion, the smoothing parameter, and the refinement factor on the performance of MNS-EWMA charts using ARL curves. We show that the MNS-EWMA control chart is an excellent indicator of changes in the quality of processes relative to SRS-Shewhart and SRS-EWMA charts. We present optimal ranges for the smoothing parameter of MNS-EWMA charts. An illustrative example with simulated data is enclosed. The results show that MNS-EWMA control charts produce significant enhancement over the traditional charts based on SRS.

Keywords:

• EWMA
• Markov Chain
• maxima nomination sampling
• np-chart
• ranked set sampling
• statistical process control

Acknowledgments

The author is thankful to the anonymous reviewers for providing useful comments that led to an improved version of the article. The author is also thankful to Dr Farzaneh Safavimanesh for reviewing the manuscript.

Disclosure statement

No potential conflict of interest was reported by the author(s).