Statistics Papers

Document Type

Journal Article

Date of this Version

1991

Publication Source

The Annals of Statistics

Volume

19

Issue

2

Start Page

1084

Last Page

1090

DOI

10.1214/aos/1176348140

Abstract

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

Comments

At the time of publication, author Dean Foster was affiliated with the University of Chicago. Currently, he is a faculty member at the Statistics Department at the University of Pennsylvania.

Keywords

comparing forecasts, worst-case behavior, mean square error

Share

COinS
 

Date Posted: 27 November 2017

This document has been peer reviewed.