Let’s pretend you manage Chuck. He’s a fairly good employee most of the time, but occasionally, he really messes up. Whenever this happens, you bring him into your office and yell at him for a bit. Chuck’s next assignment is much better. You’ve done your job as his manager. It’s not fun to yell at people, but someone has to do it.
Or do they?
Yes, it’s true – when Chuck does an unusually bad job, and you yell at him, his performance will almost always improve. What’s equally true, however, is that Chuck’s improvement has very little to do with your shouting. Instead, it has everything to do with random variation and statistics.
Being in supply chain and operations, I have a healthy respect for statistics. Much of the Toyota Production Systems (TPS), lean, Six Sigma, and quality improvement tools are a direct result of applying statistics and the scientific method to production. However, what I haven’t thought of much before is how those same principles of random variation apply to office coworkers just as much as to assembly lines.
What started me thinking about this was a great book I just finished called The Drunkard’s Walk: How Randomness Rules Our Lives by Leonard Mlodinow. In it, he tells the story of Daniel Kahneman, who won the Nobel Prize for Economics in 2002. Mlodinow writes:
In the mid-1960s, Kahneman, then a junior psychology professor at Hebrew University, agreed to perform a rather unexciting chore: lecturing a group of Israeli air force flight instructors on the conventional wisdom of behavior modification and its application to the psychology of flight training. Kahneman drove home the point that rewarding positive behavior works but punishing mistakes does not. One of his students interrupted, voicing an opinion that would lead Kahneman to an epiphany and guide his research for decades.
“I’ve often praised people warmly for beautifully executed maneuvers, and the next time they always do worse,” the flight instructor said. “And I’ve screamed at people for badly executed maneuvers, and by and large the next time they improve. Don’t tell me that reward works and punishment doesn’t work. My experience contradicts it.”
What Kahneman realized, however, is that while the yelling preceded improvement, it did not cause the improvement.
The pilots in training were all slowly improving, but you wouldn’t be able to see that improvement from one maneuver to the next. Instead, their performance was a random variation around an average skill level that was rising over months. When one maneuver was unusually bad, it was just random variation. The same held true for the exceptionally good performances – random variation around the true average skill of the training pilots.
The name of this statistical principle is regressions toward the mean. Whenever an observed results is far from the average, the next result will likely be much closer toward the average. Observations tend to gather around the average in a bell shaped curve.
This principle is widely used in production quality. We calculate upper and lower control limits on a process and expect random variation to occur. It’s only after several repeated outlying events that we intervene and investigate. If processes are within their limits, we just leave them alone. Even if several measurements are below average, we have faith that the next measurements will be higher.
Realizing that this principle holds true with humans as well is powerful. All of us will have random good and bad performances simply as a result of random variation. The majority of our performance will regress toward our true average skill level without any outside influence.
So next time Chuck has an outlying bad performance, you could yell at him, and he’ll do better the next time.
You could also watch online cat videos together – the improvement will still occur.
Why not save your lungs some stress?