Statistics for Six Sigma Green Belts with Minitab and JMP

11.2. Control Limits and Patterns

The most typical form of a control chart sets control limits at plus or minus three standard deviations of the statistic of interest (the mean, the range, the proportion, etc.). In general, control limits are computed as follows:

Computing Control Limits Process mean of the statistic ± 3 standard deviations of the statistic (11.1) so that Upper control limit (UCL) = process mean of the statistic + 3 standard deviations of the statistic Lower control limit (LCL) = process mean of the statistic – 3 standard deviations of the statistic

Once you compute these control limits from the data, you evaluate the control chart by determining whether any nonrandom pattern exists in the data. Figure 11.1 illustrates three ...