Are linear trend lines on run charts a good idea? Usually not, in Mark's view. Linear trend lines are easy to add in Excel and look authoritative, but they're sensitive to the choice of endpoints and the range of data included. The same data can produce a "trending up" or "trending down" line depending on which data points are included. Process Behavior Charts use signal rules that don't depend on fitted lines — they identify genuine shifts in the system based on statistical patterns rather than on a line of best fit. When the system genuinely has an underlying trend, there's a more sophisticated version of the Process Behavior Chart that uses a sloped center line, but the casually-added Excel trend line isn't the right tool.
How many data points do you need for a good baseline? Statistically, 15 to 20 data points is preferred. The methodology can work with as few as 6 or even 4 if that's all the data you have, with the understanding that the calculated limits will be less reliable. As more data accumulates, the limits can be recalculated and become more stable. Mark recommends starting with whatever baseline is available and improving the chart as more data comes in.
Should you set the limits as a goal? No. The limits describe what the system has been doing. The goal describes what the organization wants the system to do. The two are different. The limits are calculated from the data and reflect the system's inherent variation. The goal is a management decision. Treating the limits as a goal misuses the methodology and produces confused thinking. If the limits are too wide for comfort, the appropriate response is to work on reducing variation in the system — not to redraw the lines.
How do you introduce Process Behavior Charts to a leadership team that's used to red/green dashboards? Mark's recommendation: start with run charts. They're a smaller cognitive step from red/green than full Process Behavior Charts, and they show patterns over time that the red/green view obscures. Once leaders are comfortable with run charts, add the average line. Then add the limits and the signal rules. The shift is a change management process, not a technical implementation. Leaders who have been trained to react to every red number don't adopt the new approach immediately. The practice of showing the same data both ways — old format and new format — over time tends to make the case more effectively than a single training session.
Do Process Behavior Charts become obsolete in the age of industry 4.0 and AI? Mark didn't think so. The methodology is roughly 100 years old (the foundational work is Walter Shewhart's; Process Behavior Charts as practiced now were largely developed in the early 1940s). The methods are mature, well-validated, and don't depend on the technology used to display them. Whether the chart is drawn by hand on a bulletin board, calculated in Excel, or generated by a sophisticated platform, the underlying methodology is the same. Mark's view: Process Behavior Charts are themselves a form of decision support, filtering signal from noise so practitioners can act appropriately. The question isn't whether to replace them with newer technology but whether the new technology preserves the methodology's discipline.
What's the relationship between Process Behavior Charts and Six Sigma's DMAIC? Some Six Sigma practitioners describe control charts as belonging to the Control phase of DMAIC (Define, Measure, Analyze, Improve, Control). Mark's view: this is a misunderstanding. Process Behavior Charts are useful throughout the entire improvement cycle. The Measure phase needs them to understand baseline performance. The Analyze phase uses them to distinguish signals from noise. The Improve phase uses them to verify whether changes had effect. The Control phase uses them to sustain the gains. Restricting them to a single phase misses most of their value.
What resources does Mark recommend for someone new to Process Behavior Charts? Donald Wheeler's "Understanding Variation: The Key to Managing Chaos" is the foundational practitioner text. Mark's own book, "Measures of Success: React Less, Lead Better, Improve More," builds on Wheeler's work with additional examples and connections to Lean management practice. KaiNexus has earlier webinars that walk through the methodology in more detail, including a tutorial-style session on creating Process Behavior Charts. For practitioners who want to go deeper into the technical reasoning, Wheeler's articles on specific topics (the choice of mR-bar versus standard deviation, the handling of different data types, the cases where the X chart misses signals that the mR chart catches) are useful references.
.svg)
Copyright © 2026
Privacy Policy