Translator Disclaimer
July 2007 Accumulated prediction errors, information criteria and optimal forecasting for autoregressive time series
Ching-Kang Ing
Ann. Statist. 35(3): 1238-1277 (July 2007). DOI: 10.1214/009053606000001550

Abstract

The predictive capability of a modification of Rissanen’s accumulated prediction error (APE) criterion, APEδn, is investigated in infinite-order autoregressive (AR(∞)) models. Instead of accumulating squares of sequential prediction errors from the beginning, APEδn is obtained by summing these squared errors from stage n, where n is the sample size and 1/nδn≤1−(1/n) may depend on n. Under certain regularity conditions, an asymptotic expression is derived for the mean-squared prediction error (MSPE) of an AR predictor with order determined by APEδn. This expression shows that the prediction performance of APEδn can vary dramatically depending on the choice of δn. Another interesting finding is that when δn approaches 1 at a certain rate, APEδn can achieve asymptotic efficiency in most practical situations. An asymptotic equivalence between APEδn and an information criterion with a suitable penalty term is also established from the MSPE point of view. This offers new perspectives for understanding the information and prediction-based model selection criteria. Finally, we provide the first asymptotic efficiency result for the case when the underlying AR(∞) model is allowed to degenerate to a finite autoregression.

Citation

Download Citation

Ching-Kang Ing. "Accumulated prediction errors, information criteria and optimal forecasting for autoregressive time series." Ann. Statist. 35 (3) 1238 - 1277, July 2007. https://doi.org/10.1214/009053606000001550

Information

Published: July 2007
First available in Project Euclid: 24 July 2007

zbMATH: 1118.62097
MathSciNet: MR2341705
Digital Object Identifier: 10.1214/009053606000001550

Subjects:
Primary: 60M20
Secondary: 62F12, 62M10

Rights: Copyright © 2007 Institute of Mathematical Statistics

JOURNAL ARTICLE
40 PAGES


SHARE
Vol.35 • No. 3 • July 2007
Back to Top