Selecting the rational subgroup is crucial in developing a robust monitoring plan for dispersion of normally distributed data

Abstract

This article examines the performance of the adaptive cumulative sum (CUSUM) plans and three simultaneous CUSUM statistics with different levels of temporal memory for monitoring changes in dispersion in the steady state situation. This article demonstrates that taking a larger rational subgroup has early out-of-control detection advantages for all monitoring plans considered. The article illustrates that the CUSUM plan that seems to have the most convincing robust early detection advantages is the three CUSUM statistic with different levels of temporal memory rather than the adaptive CUSUM plans for steady state situations.

Keywords:

• Average runlength (ARL)
• Dispersion
• Monitoring
• Reference value
• Threshold

Acknowledgments

I would like to thank a reviewer for his thorough review of this article. It has enhanced its readability.