Consider a weather forecaster predicting the probability of rain for the next day. We consider tests that given a finite sequence of forecast predictions and outcomes will either pass or fail the forecaster. It is known that any test which passes a forecaster who knows the distribution of nature can also be probabilistically passed by a forecaster with no knowledge of future events. This note summarizes and examines the computational complexity of such forecasters.
ACM SIGecom Exchanges – Association for Computing Machinery
Published: Nov 1, 2008