Monitoring the process coefficient of variation without subgrouping

The coefficient of variation (CV), a measure of relative variability, is an important quality characteristic for a manufacturing process especially when the variance becomes a function of the mean. In this paper, for the first time, we develop four memory-type control charts for monitoring the CV of a normal process using individual observations, namely Crosier CUSUM (CC), EWMA, adaptive CC and adaptive EWMA charts. In addition, the sensitivities of these CV charts are also enhanced via an auxiliary information based CV estimator. The run length characteristics of these control charts are computed using Monte Carlo simulations. The proposed CV charts are also applied on a real dataset related to dowel pins.