Open Access
June, 1991 Prediction in the Worst Case
Dean P. Foster
Ann. Statist. 19(2): 1084-1090 (June, 1991). DOI: 10.1214/aos/1176348140


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 $\mathscr{D}$ of predictors, we explicitly construct a predictor $S$ that is at least as strong as every element of $\mathscr{D}$. Finite sample bounds are also given which hold uniformly on the space of all possible data.


Download Citation

Dean P. Foster. "Prediction in the Worst Case." Ann. Statist. 19 (2) 1084 - 1090, June, 1991.


Published: June, 1991
First available in Project Euclid: 12 April 2007

zbMATH: 0725.62085
MathSciNet: MR1105864
Digital Object Identifier: 10.1214/aos/1176348140

Primary: 62M20
Secondary: 62A99

Keywords: Comparing forecasts , Mean square error , worst-case behavior

Rights: Copyright © 1991 Institute of Mathematical Statistics

Vol.19 • No. 2 • June, 1991
Back to Top