Nonparametric sequential prediction of time series

Time series prediction covers a vast field of every-day statistical applications in medical, environmental and economic domains. In this paper we develop nonparametric prediction strategies based on the combination of a set of “experts” and show the universal consistency of these strategies under a minimum of conditions. We perform an indepth analysis of real-world data sets and show that these nonparametric strategies are more flexible, faster and generally outperform ARMA methods in terms of normalized cumulative prediction error. Index Terms — Time series, sequential prediction, universal consistency, kernel estimation, nearest neighbor estimation, generalized linear estimates. ∗Corresponding author.