THE PROCESS BEHAVIOR CHART

On May 16, 1924, Walter Shewhart sent his superiors at Bell Laboratories a memo proposing a simple chart Reported. A century later, the version Donald Wheeler calls the process behavior chart, or XmR chart, is still the best tool for a weekly scorecard. It tells you how much a number moves when nothing has changed, from the number’s own history.

Building one

1. List the last 12 weeksRevenue, orders, conversion rate: any number you report weekly. Leave out weeks with a big promotion, or chart promotion weeks on their own.
2. Take the averageThat’s the central line.
3. Take the moving rangesThe difference between each week and the week before, ignoring the sign. Twelve weeks give eleven moving ranges. Average them.
4. Draw the limitsAverage plus and minus 2.66 times the average moving range. Those are the natural process limits. The moving ranges get their own upper limit: 3.268 times the average moving range.

PublishedWheeler, “What Makes the XmR Chart Work?” Quality Digest, 2012; Understanding Variation, 1993. The 2.66 is 3 divided by 1.128, the constant that converts an average moving range into an estimate of the standard deviation, so the limits sit about three standard deviations from the average.

Why the moving range and not the standard deviation of all twelve weeks? Because if the number shifted partway through, the overall standard deviation includes the shift and the limits come out too wide to show it. The moving range looks only at week-to-week changes, which a shift barely touches. It’s also why the constant is 2.66 and not 2 or 3: people who swap in a rounder number get limits that are too tight and flag noise, or too loose and miss signals.

The three rules

Wheeler’s book gives three rules for spotting a signal Reported:

1. One point outside the limitsA big, sudden change. Find out what happened that week.
2. Three of four in a row closer to a limit than to the central lineA moderate change that has lasted a few weeks.
3. Eight in a row on the same side of the central lineA small, sustained shift. The easiest to miss by eye and often the most important.

For the moving range, use only the first rule: a single week-to-week jump above its upper limit Published. Everything else is noise. It gets noted, not explained.

That’s the pattern the chart exists to catch. The big drop felt like news and wasn’t. The real change was small, steady and invisible on a week-over-week report, because every one of those weeks, compared with the week before, looked normal.

With the defaults, this week’s $53,900 is 13% below the average and 15% below last week, and it’s noise: the limits run from $49,255 to $74,645 and no rule fires. Change this week to 48,000 and the verdict flips to a signal. The rule-of-eight shift in the figure above doesn’t show up here, because the tool judges one new week; for runs, keep charting week after week.

Keeping it honest

• How many weeks. Twelve is a workable start. Practitioners who teach the method suggest limits begin to firm up around 17 to 25 points Reported. Keep the same limits as you add weeks; recompute only when a signal shows the process has changed, using the weeks since the change.
• Seasons and promotions. A sale week is a planned special cause. Chart it against other sale weeks, not against normal ones. If your business is strongly seasonal, chart this year divided by the same week last year instead of raw revenue.
• Rates and counts both work. Chart the rate (conversion, repeat, click rate) and its denominator side by side, so a change in traffic doesn’t pass for a change in behavior.
• Mark the changes. Put a dated note on the chart every time something is launched, repriced or rewritten. A signal near a note is a lead; a signal without one is a question.

Do this

• Chart five numbers this week: revenue, orders, site conversion rate, revenue per email recipient and the repeat rate of your most recent full cohort. Put the limits on the scorecard, and read the three rules before anyone offers an explanation in the Monday meeting.