Process Capability for Poisson Data

Process Capability Poisson Data using Minitab is a mandatory step for practitioners doing projects where their project Y is Poisson Data.

Vinay Kumar Apr 24, 2019 6766 0

Use Capability Analysis (Poisson Distribution) to assess the capability of an in-control process when the data are from the Poisson distribution . A capable process is able to produce products or services that meet specifications. Poisson capability analysis examines the number of defects per unit of measurement (DPU).

Process Capability for Poisson Data is important for people doing projects on poisson data.
Use Capability Analysis (Poisson Distribution) to assess the capability of an in-control process when the data are from the Poisson distribution . A capable process is able to produce products or services that meet specifications. Poisson capability analysis examines the number of defects per unit of measurement (DPU).

Capability Analysis – Poisson consists of four graphs and a table of results in one window. Use the four graphs to check the assumptions for a Poisson capability analysis. The table of results provides summary statistics and a capability index that can help you assess process capability.

The U Chart is located in the upper left corner of the Process Capability Analysis .

Use the U chart to determine if the number of defects per unit of measurement is in control . The process should be in control before you assess capability. If the process is not in control, then the capability statistics will be incorrect estimates. The U chart consists of the following:

Plotted points, which represent the number of defects per unit of measurement sampled.
Center line (green), which is the average number of defects per unit of measurement sampled
Control limits (red), which are located 3 s above and below the center line, and provide a visual means for assessing when the process is out of control .

Examine the U chart for points located outside the control limits or other non-random patterns.

The Cumulative DPU graph is located in the lower left corner of the Process Capability Analysis .

The cumulative DPU(defects per unit of measurement) graph can help you determine whether you have collected enough samples to have a stable estimate of the DPU.

Ideally, this graph should show that the DPU stabilizes after several samples. This would appear as a flattening of the plotted line.

The Defect Rate graph is located in the upper right corner of the Process Capability Analysis .

The defect rate plot assesses the assumption that the number of defects is not affected by the size of the sample. Examine the plot to see if the defect rate (DPU) is randomly distributed across subgroup sizes or if a pattern is present.

Note

When your sample sizes are equal, a Poisson plot will be displayed instead of the defect rate plot. The Poisson plot plots the expected and observed number of defects. You should examine your plot to see if the plotted points are in a straight line. If not, then the assumption that the data were sampled from a Poisson distribution may be false.

The Summary Stats table is located in the lower center of the Process Capability Analysis.

The summary statistics consists of the following:

Mean DPU – an estimate of the average number of defects per unit of measurement in the sample as well as a confidence interval for the estimate.
Min and Max DPU – the minimum and maximum defects per unit of measurement from any one part of the sample.
Target DPU – the target number of defects per unit of measurement that you specified. If you did not specify a target DPU, then a target of 0 is assumed.