The Laney U' chart includes the following elements:

·    Plotted points, which represent the number of defects per unit of measurement.

·    Center line (green), which is the average number of defects per unit of measurement.

·    Control limits (red), which provide a visual means for when the process is out of control. The control limits are either fixed or varied, depending on your data and choices:

-    When your sample sizes are the same or when you choose to use an average sample size, then the control limits will be fixed.

-    When your sample sizes vary, then the control limits will vary.

·    Sigma Z, which indicates how much the control limits were adjusted to compensate for overdispersion or underdispersion:

-    A value of 1 indicates that no adjustment was necessary and that the Laney U' chart is exactly the same as a traditional U chart.

-    A value greater than 1 indicates the control limits were widened to correct for overdispersion.

-    A value less than 1 indicates the control limits were narrowed to correct for underdispersion.

You should examine the Laney U' chart for points outside the control limits and trends or other nonrandom patterns.

Minitab conducts up to four tests for special causes for the Laney U' chart, which detect points beyond the control limits and specific patterns in the data. Points that fail a test are marked with a red symbol and the number of the failed test. Complete results are available in the Session window. A failed point indicates that there is an unusual value or a nonrandom pattern, either of which may be the result of special cause variation. These points should be investigated.

The Laney U' chart for the medication error data can be summarized as follows:

·    Because the sample sizes are unequal, the control limits vary. The lower control limit is 0 (the lowest it can be) for all subgroups. The upper control limit varies around 0.025. The number of defects per unit is expected to fall within the control limits. The center line (average number of defects per unit) is approximately 0.007.

·    Subgroup 23 is outside the control limits and should be investigated.

·    Sigma Z is about 5.5, indicating that the control limits were widened to correct for overdispersion.

To see the same data plotted on a traditional U chart, see Comparing traditional U charts and Laney U' charts.