How to Predict a Golfer's Score on Day Two

If you know a golfer's score on day one and are asked to predict his score on day two, your best guess must be that it will be average. This is why the pattern is called regression to the mean. The more extreme the original score, the more regression we expect. An extremely good score suggests a very lucky day. A few of the golfers who scored 66 on day one will do even better on the second day if their luck improves. Most will do worse, because their luck will no longer be above average. Regression effects are ubiquitous, and so are misguided causal stories to explain them.