Skip to main content
Research article - Peer-reviewed, 2009

Forecasting using locally stationary wavelet processes

Xie, Yingfu; Yu, Jun; Ranneby, Bo

Abstract

Locally stationary wavelet (LSW) processes, built on non-decimated wavelets, can be used to analyse and forecast non-stationary time series. They have been proved useful in the analysis of financial data. In this paper, we first carry out a sensitivity analysis, then propose some practical guidelines for choosing the wavelet bases for these processes. The existing forecasting algorithm is found to be vulnerable to outliers, and a new algorithm is proposed to overcome the weakness. The new algorithm is shown to be stable and outperforms the existing algorithm when applied to real financial data. The volatility forecasting ability of LSW modelling based on our new algorithm is then discussed and shown to be competitive with traditional GARCH models.

Keywords

GARCH; locally stationary wavelet processes; non-decimated wavelets; sensitivity analysis; volatility forecasting

Published in

Journal of Statistical Computation and Simulation
2009, volume: 79, number: 9, pages: 1067-1082
Publisher: Taylor & Francis

Authors' information

Xie, Yingfu
Swedish University of Agricultural Sciences, Department of Forest Economics
Yu, Jun
Swedish University of Agricultural Sciences, Department of Forest Economics
Swedish University of Agricultural Sciences, Department of Forest Economics

UKÄ Subject classification

Probability Theory and Statistics

Publication Identifiers

DOI: https://doi.org/10.1080/00949650802087003

URI (permanent link to this page)

https://res.slu.se/id/publ/26284