This document covers EWMA control charts, originally proposed by Roberts (1959^)[16], as a statistical process control technique to detect small shifts in the process mean. It makes possible the faster detection of small to moderate shifts in the process mean. In this chart, the process mean is evaluated in terms of exponentially weighted moving average of all previous observations or averages.

The EWMA control chart’s application is worthwhile in particular when

—    

production rate is slow,

—    

a minor or moderate shift in the process mean is vital to be detected,

—    

sampling and inspection procedure is complex and time consuming,

—    

testing is expensive, and

—    

it involves safety risks.

NOTE            EWMA control charts are applicable for both variables and attributes data. The given examples illustrate both types (see 5.5, Annex A, Annex B and Annex C).