Using wavelet analysis to uncover the co-movement behavior of multiple energy commodity prices

Abstract

This study aims to investigate the dynamic correlations (co-movement) in between energy commodities such as WTI Crude Oil (WOIL), Brent Crude Oil (BOIL), Heating Oil and Electricity prices. To achieve this goal, we employed partial wavelet coherence (PWC) and multiple wavelet coherence (MWC). Wavelet analysis constitutes the core of these methodologies and MWC is essential to determine the dynamic correlation (co-movement) of time intervals and scales between the time series. We have developed a software program to compute PWC and MWC for quadruple data set. Coherent time intervals of the time series are determined. Vector ARMA models are shown to give a good fit due to having low mean squared errors compared to the univariate case. This allowed us to have better forecast performance.