Journal article

Publication year: 2005

Pages: 320-

Journal: Allgemeines Statistisches Archiv

Volume number: 89

Issue number: 3

DOI Link: https://doi.org/10.1007/s10182-005-0206-9

Publisher: Springer Verlag (Germany)

Abstract: 

The Hodrick-Prescott (HP) filter has become a widely used tool for detrending integrated time series. Even if the methodological literature sums up an extensive catalogue of severe criticism against an econometric analysis of HP filtered data, the original Hodrick and Prescott (1980, 1997) suggestion to measure the strength of association between economic variables by a regression analysis of corresponding HP filtered time series appears to be very popular. This might be justified if HP induced distortions were quantitatively negligible in empirical applications. However, the simulated regression analyses presented in our paper demonstrate that any attempts of inference based on HP prefiltered series are challenged by a serious risk of spurious regression results.

Harvard Citation style: Meyer, M. and Winker, P. (2005) Using HP Filtered Data for Econometric Analysis: Some Evidence from Monte Carlo Simulations, Allgemeines Statistisches Archiv, 89(3), Article 303. p. 320. https://doi.org/10.1007/s10182-005-0206-9

APA Citation style: Meyer, M., & Winker, P. (2005). Using HP Filtered Data for Econometric Analysis: Some Evidence from Monte Carlo Simulations. Allgemeines Statistisches Archiv. 89(3), Article 303, 320. https://doi.org/10.1007/s10182-005-0206-9