AN ALTERNATIVE DESIGN FOR THE VARIABLE SAMPLE SIZE COEFFICIENT OF VARIATION CHART BASED ON THE MEDIAN RUN LENGTH AND EXPECTED MEDIAN RUN LENGTH

Control charts for monitoring the coefficient of variation (CV) are attracting increasing attention in recent years. These charts are able to monitor processes with an unstable mean and/or standard deviation, but has a stable CV. Existing CV charts are designed based on the average run length (ARL) criterion. However, this paper has shown that designs based on the ARL criterion could result in misinterpretation of the chart's actual performance. Hence, this paper proposes alternative designs for the VSS CV chart, based on the median run length (MRL) and expected median run length (EMRL) criteria. This paper also compares the performance of the VSS CV chart with that of the Exponentially Weighted Moving Average (EWMA) and Shewhart CV charts, based on the proposed designs. Subsequently, this paper shows the implementation of the proposed designs on an industrial example.