Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/104411 
Year of Publication: 
2014
Series/Report no.: 
Munich Discussion Paper No. 2014-1
Publisher: 
Ludwig-Maximilians-Universität München, Volkswirtschaftliche Fakultät, München
Abstract: 
The Hodrick-Prescott filter is the probably most popular tool for trend estimation in economics. Compared to other frequently used methods like the Baxter-King filter it allows to estimate the trend for the most recent periods of a time series. However, the Hodrick- Prescott filter suffers from an increasing excess variability at the margins of the series inducing a too flexible trend function at the margins compared to the middle. This paper will tackle this problem using spectral analysis and a flexible penalization. It will show that the excess variability can be reduced immensely by a flexible penalization, while the gain function for the middle of the time series is used as a measure to determine the degree of the flexible penalization.
Subjects: 
Hodrick-Prescott filter
spectral analysis
trend estimation
gain function
flexible penalization
JEL: 
C22
C52
Persistent Identifier of the first edition: 
Document Type: 
Working Paper

Files in This Item:
File
Size





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.