Quantifying process improvement impact using a 30,000-foot-level chart is very beneficial for a Lean Six Sigma project or Kaizen event deployments.
Quantifying Process Improvement and 30,000-foot-level Predictability Statements
Note: Content of this webpage is from Chapters 12 and 13 of Integrated Enterprise Excellence Volume III – Improvement Project Execution: A Management and Black Belt Guide for Going Beyond Lean Six Sigma and the Balanced Scorecard, Forrest W. Breyfogle III.
Enhancements from process improvement efforts (e.g., Lean Six Sigma project or Kaizen event) should be accompanied by statistical validation and quantification of the benefits. This can be accomplished by tracking a process over time at the 30,000-foot-level1, as described in 30,000-foot-level Reports with its Predictive Measurements.
With a high-level process-output tracking at the 30,000-foot-level, there will be an infrequent subgrouping/sampling plan such that the typical variability from input variables that could affect the response will occur between these subgroupings. An infrequent subgrouping/sampling interval could be day, week, or month, where responses from differing people, departments, machines, and so forth would be captured within each subgroup.
This mixture of input variability within subgroups for 30,000-foot-level charting is different from traditional statistical control charting, which has a primary focus of controlling a process through the identification of special- cause events that can be resolved in a timely fashion. 30,000-foot-level charting does not offer timely identification of process changes but instead provides a high-level view of how the process is performing from a customer-of-the-process point of view.
From a high-level, 30,000-foot-level point of view, specific differences between inputs that could affect a response are not a primary concern. Instead focus is given to whether the process is stable (consistently performing over time) and how well the process is performing relative to objectives or desires for process performance. An individuals control chart is needed to assess process stability from a 30,000-foot-level point of view. Traditional x-bar and R charts, p-charts, and c-charts cannot provide a 30,000-foot-level stability assessment, since between-subgroup variability for these control charting techniques has no impact on the control chart’s upper and lower control chart limit calculations.
For a detailed discussion of traditional control charting shortcomings, see:
- X-bar and R Control Chart: Issues and Resolution
- P-chart: Issues and Resolution
- C-chart: Issues and Resolution
30,000-foot-level charting consists of two steps. The first step is to determine if the process has a recent region of stability, where this stability region could be six days, six weeks, six months, or six years. If the process does have a recent region of stability, the second step is to describe how the process is performing.
Processes will inherently have variability. Some processes have a great deal of variability, while other processes do not experience much variation. Decisions relative to what action or non-action should be taken in a process should consider this variability and the statistics or probability that accompanies this variability. However, often decisions are made using only a table of numbers, a pie chart, stacked bar chart, red-yellow-green scorecards, or variances to goals, which do not include variability in their reporting process. (For a more detailed discussion and illustration of the shortcomings from these performance-reporting methods see: Performance Reporting (KPI Reports): Issues and Resolution).
Assessing Process Stability and Quantifying Process Predictability
Time-series data can be continuous or pass/fail attribute proportion. An individuals control chart is used in general for 30,000-foot-level reporting to assess process stability. When a process is considered stable at the 30,000-foot-level, the next steps are to determine how the process is performing and to provide a prediction statement.
If a specification exists or the response is a pass/fail attribute proportion, a 30,000-foot-level predictability statement would be made about percentage or proportion non-conformance. If the response is continuous and there is no specification, a statement is made about its median response and 80% frequency of occurrence values. When the response is pass/fail attribute, a statement can be made relative to non-conformance directly from the chart or data calculations from the most recent region of stability. When a response is continuous, a probability plot is used to estimate process performance relative to a specification or to provide a median and 80% frequency of occurrence rate.
To some, a probability plot can initially appear intimidating; however, interpretation of this chart is not complex. With the probability plot, the x-axis is the response, while the y-axis is percent less than the value on the x-axis. Other articles referenced below provide a more detailed explanation.
With 30,000-foot-level reporting, a statement is provided at the bottom of the graph stating whether the process is predictable or not. If the process is predictable, a prediction statement is made. This prediction statement provides a chart reviewer a quick assessment of how the process is performing. The accompanying charts also give a visual representation of the variability that accompanies the process, which can be examined in further detail, if so desired.
Demonstrating Process Change
This section of this article illustrates an example 30,000-foot-level report-out with its tracking over time and quantification of process performance, while later referenced articles provide a more detailed explanation of the mechanics to create the charts.
Figure 1 illustrates a 30,000-foot-level response change (e.g., from completing a Lean Six Sigma project) for a continuous response when there are no specifications, while Figure 2 illustrates a 30,000-foot-level response change for an attribute response.
Firgure 1: 30,000-foot-level Chart (Continuous Response, No Specification)2
Firgure 2: 30,000-foot-level Chart (Pass/Fail Attribute Response)2
Providing Predictive Measurements using 30,000-foot-level Charting
For more information about 30,000-foot-level reporting see:
- 30,000-foot-level Performance Reporting Applications
- 30,000-foot-level Charting: One Sample per Subgroup
- 30,000-foot-level Charting: Multiple Samples in Subgroups
- 30,000-foot-level Charting: Attribute Pass/Fail Data
- 30,000-foot-level Charting: Infrequent Failures
- 30,000-foot-level Charting: Non-normal Data
Business System Application of 30,000-foot-level Reporting
Traditional organizational performance measurement reporting systems can utilize a table of numbers, stacked bar charts, pie charts, and red-yellow-green-goal-based scorecards. For a given situation, one person may choose one reporting scheme, while another uses a completely different approach. These differences can lead to a different conclusion about what is happening and what should be done. In addition, described traditional reporting methods provide only an assessment of historical data and make no predictive statements or statistical assessment of whether a process has changed or not. These charting and metric performance-reporting shortcomings are overcome with 30,000-foot-level reporting.
Organizations benefit when then transition their traditional scorecards and dashboards to 30,000-foot-level reporting, as referenced by the ten illustrations in the article Predictive Dashboard and Scorecard Reporting . This predictive performance reporting can be automatically updated using Enterprise Performance Reporting System (EPRS) software.
An Integrated Enterprise Excellence (IEE) Business Management System with 30,000-foot-level reporting addresses the business scorecard and improvement issues described in a 1-minute video:
- 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
- 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) Business Process Management System and its 30,000-foot-level metric approach for quantifying process improvement.