Wavelet Estimation of Kondratieff Waves: An Applica-tion to Long Cycles in Prices and World GDP


Author: Gallegati, Marco
Almanac: Kondratieff waves:Cycles, Crises, and Forecasts

Abstract

In this paper we apply wavelet analysis to the detection of long waves in wholesale price index for France, the UK and the US because wavelets can easily overcome most of the methodological difficulties experienced in previ-ous methods.

The advantages of using wavelet multiresolution decomposition analysis for the analysis of long waves studied by Kondratieff are manifold: 1) long wave components are easily obtainable through multiresolution decomposition analysis; 2) no preliminary correction is needed; and 3) they can handily detect cycles that are not easily visible in trending series (as it is the case of the wholesale price index in the post-WWII period).

Comparisons with the chronology in the literature on long wave cycles for prices and with recent results for world GDP growth rates indicate that wavelet analysis can provide a reliable and useful statistical methodology in order to analyze the dynamics of long waves in historical time series.

Keywords: long wave cycles, wavelet analysis, wholesale prices, world GDP.