U-Chart is an attribute control chart used when plotting:
2) POISSON ASSUMPTIONS SATISFIED
3) VARIABLE SAMPLE SIZE (subgroup size)
Each observation is independent. This chart is used to develop an upper control limit and lower control limit (UCL/LCL) and monitor process performance over time. It plots the number of defects per unit sampled in a variable sized sample.
If defect level is small, use the Poisson Distribution exact limits, DPU < 1.5.
Used to detect shifts >1.5 standard deviations. In order to detect smaller shifts there are other charts that can be applied to variable and attribute data such as Exponentially Weighted Moving Average (EWMA) and Cumulative Sum of Quality Characteristic Measurement (CUSUM).
Most statistical software programs automatically calculate the UCL and LCL to quickly examine control offer visual insight to the performance over time.
Shown below is the data set plotted using a U-Chart.
The chart indicates that the process is in control. The control tests that were used all passed in this case.
Recall there are a variety of control tests and most statistical software programs allow you to select and modify these criteria.
Six Sigma Modules
The following presentations are available to download
Green Belt Program 1,000+ Slides
Cause & Effect Matrix
Central Limit Theorem
1-Way Anova Test
Correlation and Regression