The Signal and the Noise: Why So Many Predictions Fail-but Some Don't

by Nate Silver

Specifically, I split the sample data into even- and odd-numbered months; if a player is truly skilled, he should be winning in the even-numbered months as well as the odd-numbered ones. I then applied a regression analysis to predict a player’s win rate (measured as big blinds won per one hundred hands) from one half of the sample to the other; the results of the regression are taken to be tantamount to the player’s long term success rate. The variables in the regression were a player’s win rate, multiplied by the natural logarithm of the number of hands who he played, along with a variable indicating how many hands he played of the ones he was dealt. Players who were too tight or too loose were considerably less likely to replicate their success from one period to the next, holding other factors equal—in fact, this was often a better predictor of a player’s out-of-sample win rate than the past win rate itself, unless he had played a very large number of hands.