Journal Article

Forecasting Time Series Subject to Multiple Structural Breaks

M. Hashem Pesaran, Davide Pettenuzzo and Allan Timmermann

in The Review of Economic Studies

Published on behalf of Review of Economic Studies Ltd

Volume 73, issue 4, pages 1057-1084
Published in print October 2006 | ISSN: 0034-6527
Published online October 2006 | e-ISSN: 1467-937X | DOI: http://dx.doi.org/10.1111/j.1467-937X.2006.00408.x
Forecasting Time Series Subject to Multiple Structural Breaks

More Like This

Show all results sharing these subjects:

  • Single Equation Models; Single Variables
  • Econometric Modelling
  • Money and Interest Rates

GO

Show Summary Details

Preview

This paper provides a new approach to forecasting time series that are subject to discrete structural breaks. We propose a Bayesian estimation and prediction procedure that allows for the possibility of new breaks occurring over the forecast horizon, taking account of the size and duration of past breaks (if any) by means of a hierarchical hidden Markov chain model. Predictions are formed by integrating over the parameters from the meta-distribution that characterizes the stochastic break-point process. In an application to U.S. Treasury bill rates, we find that the method leads to better out-of-sample forecasts than a range of alternative methods.

Keywords: C22; C53; E43; E47

Journal Article.  10754 words.  Illustrated.

Subjects: Single Equation Models; Single Variables ; Econometric Modelling ; Money and Interest Rates

Full text: subscription required

How to subscribe Recommend to my Librarian

Users without a subscription are not able to see the full content. Please, subscribe or login to access all content.