Enhanced Control Charts for Defective Proportions with Predictive Process Capability Statement

Enhanced control charts for defective proportions with a predictive process capability statement (when appropriate) is available in one chart with a 30,000-foot-level report out. This futuristic form of reporting is an enhancement to the traditional p-charting approach for this situation.

The control limits for a p chart are calculated as a function of within subgroup process variability. If a process has between subgroup common cause variability, control limits for p chart calculations can yield false out of control signals.  The ASQ  Quality Progress published article titled “Control Charting At The 30,000-Foot-Level, Part II” by Forrest Breyfogle addresses this issue and provides an alternative approach for calculating these statistical process control (SPC) control limits. A PDF of this article is available below.

Control Charts for Defective Proportions Example: Limits for p chart

The following p chart has many out of control signals

control charts for defective proportions, Control Limits for p chart, Traditional Approach

 

Control Charts for Defective Proportions Example: Control Limits for Individuals Chart

However, these out of control signals do not occur if the non-conformance rate were plotted on an individuals chart.

 

 

Traditionally attribute control charts control limits for p chart are derived from within-subgroup variability and assume special cause signal should be made whenever the binomial situation for the process overall is not maintained. This does not occur while sampling standard deviation for the individuals chart is calculated from between-subgroup variability.  This is a big deal that is not traditional discussed.

This PDF article below elaborates more on the mathematics behind these statements.  This article also describes the creation of a process capability index statement that is easy for others to understand.

Example: Alternative control limits for p chart

A 30,000-foot-level chart is an alternative where the non-conformance rates are tracked in an individuals chart to determine process stability, where subgroups sample need to have a similar value.  Traditional p chart reporting for a high-level assessment is not the real world, for most situations.  In addition, if a process has a recent region of stability, a prediction statement is provided at the bottom of the chart in words that are easy to understand.

General information about 30,000-foot-level reporting:

Application of 30,000-foot-level charting to an organizational enterprise scorecard, operational excellence and improvement system:

A Minitab add-in (no charge) is available for the easy creation of 30,000-foot-level charts

How to create 30,000-foot-level charts for a variety of performance measurement situations is described in:

For more information about how 30,000-foot-level reporting addresses issues with p-charts and attribute response process capability reporting, download the published Control ASQ November 2004 ″Charting At The 30,000-Foot-Level, Part II″ PDF article. 

 

Contact Us to set up a time to discuss with Forrest Breyfogle how your organization might gain much from IEE 30,000-foot-level reports.