Deflated Sharpe ratio

The multiple-testing correction to the Sharpe ratio: it derives an expected-maximum-Sharpe benchmark from the number of trials run and evaluates the probability the observed Sharpe beats that noise benchmark, also correcting for skew, kurtosis, and sample length. A raw Sharpe can deflate to near a coin flip once the trial count is accounted for.

First used in Lesson 2.8 · Overfitting statistics and pre-registration — the lesson that makes this term real.