U Chart

Overview | How to | Example

 


 

Overview

The U Chart is a control chart used to track the number of defects per unit sampled and detect signs of special causes. The U Chart is useful when the subgroup size varies. The data is assumed to follow a Poisson distribution and the average number of defects is estimated from the data.

 


 

How to

At the Excel Menu (For Excel 2007, go to Add-ins first)

  1. Choose ProcessMA > Control Charts > Attributes Charts > U

  2. In Variable, select the column containing the data (Positive integer)

  3. In Subgroup Sizes , select the column containing subgroup sizes (Optional, Positive integer, >=Variable)

  4. In Constant Subgroup Size , enter the subgroup size if it is constant (Positive integer, >=Variable)

  5. In Historical Mean, enter the population mean, otherwise it will be estimated by the sample mean (Optional, Numeric)

  6. In Control Limit Multiples, enter the position to draw the upper and lower control limits. Multiple entries must be separated by commas (Optional, Numeric, >0, Up to 3 multiples)

  7. In Lower Limit Bound, enter the bound on the lower control limit (Optional, Numeric)

  8. In Upper Limit Bound, enter the bound on the upper control limit (Optional, Numeric)

  9. In Phase, select the column containing the phase indicators (Optional, >=2 distinct values)

  10. Check the various checkboxes to perform respective tests

  11. Click OK

 

 

Example

You work in a paper manufacturing plant and you need the control the quality of the paper. For each batch, you inspect a certain quantity to make sure that the papers are ‘white enough’ for quality control. You want to use the U chart to help you monitor.

  1. Open data worksheet by choosing ProcessMA > Tools > Data

  2. Choose ProcessMA > Control Charts > Attributes Charts > U

  3. In Variable, select S - Stained

  4. In Subgroup Sizes , select T - Sampled

  5. Click OK

 

Results & Interpretation

Sample 20 is outside the control limit and you may want to investigate that batch for quality issues.

 


 

Copyright © ProcessMA