EWMA or Cusum charts are the best charts for detecting process shifts less than 1σ.
Typical control charts, such as Xbar & R and X & Mr, indicate whether or not a process is statistically stable. They detect process changes greater than 1.5σ and, because of this, are not the best tool to detect small process shifts. To detect small shifts, defined as shifts less than 1σ, use the EWMA or Cusum charts.
EWMA (Exponential Weighted Moving Average) chart weights moving average values according to time. The more recent the value, the greater the weight assigned to that value and, in effect, the greater the emphasis given to that value.
The Cusum (Cumulative Sum) chart plots the cumulative sum of deviations from a target value. These charts detect shifts from the process mean as small as 0.5σ. Cusum charts are plotted in 2 forms – V-Mask and Tabular Cusum (available in WinSPC).
Although EWMA and Cusum charts are very valuable in monitoring continuous processes where small changes have significant effects, it is not recommended that they be used as process improvement tools. Rather, process improvement decisions should be made using other tools such as control, pre-control and Pareto charts.
Steven Wachs, Principal Statistician
Integral Concepts, Inc.
Integral Concepts provides consulting services and training in the application of quantitative methods to understand, predict, and optimize product designs, manufacturing operations, and product reliability. www.integral-concepts.com