Statistics for Six Sigma Green Belts with Minitab and JMP

11.3. Rules for Determining Out-of-Control Points

The simplest rule for detecting the presence of a special cause is one or more points falling beyond the Three-Sigma limits. The control chart can be made more sensitive and effective in detecting out-of-control points by considering other signals and patterns that are unlikely to occur by chance alone. For example, if only common causes are operating, you would expect the points plotted to approximately follow a bell-shaped normal distribution. Figure 11.2 presents a control chart in which the area between the UCL and LCL is subdivided into bands, each of which is 1 standard deviation wide. These additional limits, or zone boundaries, are useful in detecting other unlikely patterns of data points. ...