Statistics and Its Interface

Volume 6 (2013)

Number 4

A local vector autoregressive framework and its applications to multivariate time series monitoring and forecasting

Pages: 499 – 509

DOI: https://dx.doi.org/10.4310/SII.2013.v6.n4.a8

Authors

Ying Chen (Department of Statistics & Applied Probability, National University of Singapore, Singapore)

Bo Li (Department of Statistics & Applied Probability, National University of Singapore, Singapore)

Linlin Niu (Wang Yanan Institute for Studies in Economics (WISE), Xiamen University, Xiamen, China)

Abstract

Our proposed local vector autoregressive (LVAR) model has time-varying parameters that allow it to be safely used in both stationary and non-stationary situations. The estimation is conducted over an interval of local homogeneity where the parameters are approximately constant. The local interval is identified in a sequential testing procedure. Numerical analysis and real data applications are conducted to illustrate the monitoring function and forecast performance of the proposed model.

Keywords

adaptive estimation, multivariate time series, non-stationarity, yield curve

Full Text (PDF format)

Published 10 January 2014