To read this content please select one of the options below:

A VAR Approach to Forecasting Multivariate Long Memory Processes Subject to Structural Breaks

^aUniversité catholique de Louvain, Belgium; National Tsing Hua University, Department of Quantitative Finance, Taiwan; Peking University, HSBC Business School, China.

^bHong Kong Baptist University, Department of Economics, China.

Essays in Honor of Cheng Hsiao

ISBN: 978-1-78973-958-9, eISBN: 978-1-78973-957-2

Publication date: 15 April 2020

Abstract

This chapter extends the univariate forecasting method proposed by Wang, Luc, and Hsiao (2013) to forecast the multivariate long memory model subject to structural breaks. The approach does not need to estimate the parameters of this multivariate system nor need to detect the structural breaks. The only procedure is to employ a VAR(k) model to approximate the multivariate long memory model subject to structural breaks. Therefore, this approach reduces the computational burden substantially and also avoids estimation of the parameters of the multivariate long memory model, which can lead to poor forecasting performance. Moreover, when there are multiple breaks, when the breaks occur close to the end of the sample or when the breaks occur at different locations for the time series in the system, our VAR approximation approach solves the issue of spurious breaks in finite samples, even though the exact orders of the multivariate long memory process are unknown. Insights from our theoretical analysis are confirmed by a set of Monte Carlo experiments, through which we demonstrate that our approach provides a substantial improvement over existing multivariate prediction methods. Finally, an empirical application to the multivariate realized volatility illustrates the usefulness of our forecasting procedure.

Keywords

Acknowledgements

Acknowledgments

We thank Cheng Hsiao, Luc Bauwens, Christian M. Hafner, Kevin, Y. K. Yang, and Chryso-valantis Vasilak, as well as the participants at econometrics seminar of CORE, University of Warwick, University of Amsterdam and Advanced in Econometrics conference for insightful suggestions and comments.

Citation

Wang, C.S.H. and Wan, S.K. (2020), "A VAR Approach to Forecasting Multivariate Long Memory Processes Subject to Structural Breaks", Li, T., Pesaran, M.H. and Terrell, D. (Ed.) Essays in Honor of Cheng Hsiao (Advances in Econometrics, Vol. 41), Emerald Publishing Limited, Leeds, pp. 105-141. https://doi.org/10.1108/S0731-905320200000041004

Publisher

:

Emerald Publishing Limited