Prediction in the worst case. (English) Zbl 0725.62085

Summary: A predictor is a method of estimating the probability of future events over an infinite data sequence. One predictor is as strong as another if for all data sequences the former has at most the mean square error (MSE) of the latter. Given any countable set \({\mathcal D}\) of predictors, we explicitly construct a predictor S that is at least as strong as every element of \({\mathcal D}\). Finite sample bounds are also given which hold uniformly on the space of all possible data.


62M20 Inference from stochastic processes and prediction
62A01 Foundations and philosophical topics in statistics
Full Text: DOI