Predictive Analytics Models Example Attribute Data: 30,000-foot-level Charting

This predictive analytics models example attribute data illustration shows the value of 30,000-foot-level reporting in the Integrated Enterprise Excellence (IEE) Business Management System.

This “30,000-foot-level Charting: Attribute Data” discussion addresses stability and predictability of an attribute-process output response over time.

Predictive Analytics Models Example Attribute Data: 30,000-foot-level Charting

Attribute, pass/fail proportion data, can be monitored over time for stability and then, when a process is stable, provide a prediction statement.

Consider that the attribute proportion data in Table 1 were collected using an infrequent subgrouping/sampling plan, which is consistent with a 30,000-foot-level charting methodology1

Traditionally a p-chart methodology would be used to track this type of data over time; however, there are issues with this approach as described in P-charts: Issues and Resolution.

 

Predictive Analytics Models Example Attribute Data: 30,000-foot-level Charting: Data Set

Table 1: Time-Series Data from Process

 

The 30,000-foot-level chart, as shown in Figure 1, indicates that the process is stable. When a process has a recent region of stability, it can also be said to be predictable. When this occurs, we can use historical data to make a statement about what we might expect in the future, assuming things stay the same; e.g., the center line of the chart if no transformations are needed to create the 30,000-foot-level chart, and the subgroup sizes are approximately the same.

 

Predictive Analytics Models Example Attribute Data: 30,000-foot-level Charting Output

Figure 2: 30,000-foot-level Chart of Non-conformance Rate2

 

The process capability/performance metric for this process can be said to have a non-compliance rate about 0.021, which is noted at the bottom of the chart. That is, since the process is in control/predictable, it is estimated that the future non-conformance rate will be about 0.021, unless a significant change is made to the process or something else happens that either positively or negatively affects the overall response. This situation also implies that Band-Aid or firefighting efforts can waste resources when fundamental business process improvements are really what are needed.

If improvement is needed for this 30,000-foot-level metric, a Pareto chart of defect reasons can give insight to where improvement efforts should focus. The most frequent defect type could be the focus of a new Lean Six Sigma project. For this Lean Six Sigma implementation strategy, one could say common-cause measurement improvement needs are pulling for the creation of a Lean Six Sigma project.

Reference the article P-charts: Issues and Resolution for a more detailed explanation of the methodology summarized in this paper.

 

Predictive Analytics Models Example Attribute Data: 30,000-foot-level Charting Applications

The described 30,000-foot-level charting technique has many applications, as described in 30,000-foot-level Performance Reporting Applications.

IEE Predictive Analytics Models addresses traditional business scorecard reporting and improvement issues that are described in a 1-minute video:

 

predictive analytics models example attribute data video

 

Predictive Analytics Models Example Attribute Data: References

  1. Forrest W. Breyfogle III, Integrated Enterprise Excellence Volume III – Improvement Project Execution: A Management and Black Belt Guide for Going Beyond Lean Six Sigma and the Balanced Scorecard, Bridgeway Books/Citius Publishing, 2008
  2. Figure created using Enterprise Performance Reporting System (EPRS) Software

 

Contact Us to set up a time to discuss with Forrest Breyfogle how your organization might gain much from an Integrated Enterprise Excellence (IEE) predictive analytics model approach for attribute and other types of data.