On fractional filtering versus conventional filtering in economics

Abstract

In this study, we compare the Hodrick-Prescott Filter technique with the Fractional filtering technique that has recently started to be used in various applied sciences like physics, engineering, and biology. We apply these filtering techniques to quarterly GDP data from Turkey for the period 1988:1-2003:2. The filtered series are analyzed using Minimum Square Error (MSE) and real life evidence. In the second part of the study, we use simulated data to analyze the statistical properties of the aforementioned filtering techniques. © 2009 Elsevier B.V. All rights reserved.