A comparison between the performances of synthetic and EWMA charts for monitoring the coefficient of variation

Wei Lin Teoh, Michael B. C. Khoo, W. C. Yeong, Sin Yin Teh

Research output: Contribution to journalArticle

Abstract

The coefficient of variation (CV) is a vital and widely used dimensionless measure of variability. The CV has many applications in scientific areas and is receiving growing attention in modern Statistical Process Control. It is well known that both the Synthetic and exponentially weighted moving average (EWMA) charts are very effective in detecting small to moderate changes in the CV. Therefore, a thorough comparison between the performances of these two optimal control charts is discussed in this paper. All the cases for detecting increasing and decreasing shifts in the nominal CV under both the zero- and steady-state modes are included in our study. The results reveal that the optimal EWMA CV-squared (EWMA-CV2) chart outperforms the Synthetic CV (Syn-CV (chart for detecting small changes in the CV under the zero-state mode. However, for large increases in the CV, the Synthetic- CV chart is preferred. For the steady-state case, the EWMA-CV2 chart is superior to the Synthetic- CV chart for detecting all levels of increases and decreases in the CV.
Original languageEnglish
Pages (from-to)16-20
JournalJournal of Scientific Research and Development
Volume3
Issue number1
Publication statusPublished - 2016

Fingerprint Dive into the research topics of 'A comparison between the performances of synthetic and EWMA charts for monitoring the coefficient of variation'. Together they form a unique fingerprint.

Cite this