Detrending economic time series: a Bayesian generalization of the Hodrick-Prescott filter

Thomas M. Trimbur
Additional contact information
Thomas M. Trimbur: Faculty of Economics, Cambridge University, UK, Postal: Faculty of Economics, Cambridge University, UK

Journal of Forecasting, 2006, vol. 25, issue 4, pages 247-273

Abstract: This article develops a new method for detrending time series. It is shown how, in a Bayesian framework, a generalized version of the Hodrick-Prescott filter is obtained by specifying prior densities on the signal-to-noise ratio (q) in the underlying unobserved components model. This helps ensure an appropriate degree of smoothness in the estimated trend while allowing for uncertainty in q. The article discusses the important issue of prior elicitation for time series recorded at different frequencies. By combining prior expectations with the likelihood, the Bayesian approach permits detrending in a way that is more consistent with the properties of the series. The method is illustrated with some quarterly and annual US macroeconomic series. Copyright © 2006 John Wiley & Sons, Ltd.

Downloads: (external link)
http://hdl.handle.net/10.1002/for.987 Link to full text; subscription required (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Access Statistics for this article

Journal of Forecasting is edited by Derek W. Bunn

More articles in Journal of Forecasting from John Wiley & Sons, Ltd.
Series data maintained by Christopher F. Baum ().