Friday, January 27, 2017

Regression to the mean - Why we would all be better off if we ignored Trump’s tweets

O’Donnell’s answer to the annual question "What scientific term or concept ought to be more widely known?":
My candidate is an old, simple, and powerful one: the law of regression to the mean. It’s a concept from the discipline of statistics, but in real life it means that anomalies are anomalies, coincidences happen (all the time, with stunning frequency), and the main thing they tell us is that the next thing to happen is very likely to be a lot more boring, ordinary, and predictable. Put in the simplest human terms, it teaches us not to be so excitable, not to be so worried, not to be so excited: Life really will be, for the most part, boring and predictable.
The ancient and late antique intellectuals whom I spend my life studying wouldn’t talk so much about miracles and portents if they could calm down and think about the numbers. The baseball fans thrilled to see the guy on a hitting streak come to the plate wouldn’t be so disappointed when he struck out. Even people reading election returns would see much more normality lurking inside shocking results than television reporters can admit.
Heeding the law of regression to the mean would help us slow down, calm down, pay attention to the long term and the big picture, and react with a more strategic patience to crises large and small. We’d all be better off.

No comments:

Post a Comment