◆ The PatternExtreme outcomes are followed by less extreme ones — not a force, just arithmetic
// Extreme outcomes are followed by less extreme ones — not a force, just arithmetic
Francis Galton measured parents and children in the 1880s and noticed something odd: the tallest parents tended to have children who were tall — but not quite as tall. The shortest parents had children who were short — but not quite as short. He called it “regression toward mediocrity.”
This is not a biological force pulling everyone to average. It is arithmetic. Any measurement is part signal, part luck. When luck runs extremely high, it is unlikely to run that high again. So the next measurement drifts back toward the centre. A fund manager’s best quarter is followed by a more ordinary one. A student’s worst exam is followed by a better one. Nothing changed except the luck component.
The pattern: whenever you select on an extreme, the follow-up will be less extreme. Understanding this prevents you from inventing explanations for what is simply reversion.
Correlation55%
First measurement vs. second — the pull toward centre
What to rememberAfter any extreme result, bet on something more ordinary next — and resist inventing a story for the change.
References
[1] Galton, F. (1886). Regression Towards Mediocrity in Hereditary Stature. Journal of the Anthropological Institute, 15, 246–263. doi:10.2307/2841583
[2] Kahneman, D. (2011). Thinking, Fast and Slow, Ch. 17: Regression to the Mean. Farrar, Straus and Giroux.
[3] Barnett, A. G., van der Pols, J. C. & Dobson, A. J. (2005). Regression to the mean: what it is and how to deal with it. International Journal of Epidemiology, 34(1), 215–220. doi:10.1093/ije/dyh299
Pattern bridge: The Bayesian A/B testing topic wrestles with the same trap — is the improvement real, or just regression to the mean?