A simple randomized algorithm for consistent sequential prediction of ergodic time series

We present a simple randomized procedure for the prediction of a binary sequence. The algorithm uses ideas from recent developments of the theory of the prediction of individual sequences. We show that if the sequence is a realization of a stationary and ergodic random process then the average number of mistakes converges, almost surely, to that of the optimum, given by the Bayes predictor.

MoreLess

Year of publication:	1998-04
Authors:	Györfi, László ; Lugosi, Gábor ; Morvai, Gusztáv
Institutions:	Department of Economics and Business, Universitat Pompeu Fabra
Subject:	Prediction \| ergodic processes \| pattern classification

More details

Extent:	application/pdf
Series:	Economics Working Papers.
Type of publication:	Book / Working Paper
Language:	English
Classification:	C13 - Estimation
Source:	RePEc - Research Papers in Economics

Persistent link: https://www.econbiz.de/10005572669