Signals, not noise! Patterns, not points!

This is my mantra to everyone who is still comparing performance this month to last month, to the same month last year, or to year-to-date:

Signals, not noise! Patterns, not points!

Natural variation always exists in everything: annual rainfall, daily share prices, monthly unemployment rates.

Just because two values of a measure differ, doesn’t mean there’s been a change.

That’s because abnormal variation doesn’t always exist in everything. It’s there sometimes, and only when there’s been an assignable cause at play.

When we report and use our performance measures, we need to be sure we only respond when performance truly has changed (or is refusing to improve) and thus needs our attention. We need to easily distinguish natural variation from abnormal variation.

There are three practices to master the “Signals, not noise! Patterns, not points!” mantra.

Use run charts to display and interpret the measures.

Run charts are simply line graphs—where your measure’s values are displayed over time as a continuous line—which include at least 20 points of your measure. So for a monthly measure, you’d include around 2 years’ worth of values.

The run chart also has a long term mean line included, calculated from the first 20 points, and changed only when there is a statistically real shift or trend.

Run charts make it easier to see the true signals, distinct from normal variation.

Include cause analysis with measures.

If your run chart shows a change in performance, then do a little investigating and further data analysis to find likely causes.

You can report this cause analysis with your measures, using Pareto charts or histograms or other graphs showing the occurrence and behaviour of the most likely causes.

Respond by mitigating the causes.

Performance measurement’s purpose is to improve performance. And to improve performance, we need to remove the constraints that are limiting or holding higher performance back. And those constraints are the root causes.

No other method will improve performance. So it’s causes that our action must be focused on.

If your colleagues or clients still compare performance this month to last month, to the same month last year, or to year-to-date, they need your help to master these three practices, fast. They’ve wasted more time and effort than they realise.

ABOUT THE AUTHOR

Stacey Barr is the Performance Measure Specialist, helping strategic planners, business analysts and performance measurement officers confidently facilitate their organisation to create and use meaningful performance measures with lots of buy-in. Sign up for Stacey’s free email tips at www.staceybarr.com/202tipsKPI.html and receive a complimentary copy of her renowned e-book “202 Tips for Performance Measurement”.