Determinants of Commodity Futures Prices: Decomposition Approach

Developing models to analyze time series is a very sophisticated, time-consuming, but interesting experience for researchers. Commodity price component determination challenging due remarkable volatility, uncertainty, and complexity in the futures market. This study aims determine components that drive market of commodity futures. utilized decomposition methods, empirical mode (EMD), variational (VMD), three prices data: corn from agricultural products, crude oil energy, gold industrial metal. We applied these techniques decompose daily data each different periods frequencies into individual intrinsic functions EMD modes VMD. used hierarchical clustering method Euclidean distance approach classify IMFs high-frequency, low-frequency, trend. Next, applying statistical measures, particularly, Pearson product-moment correlation coefficient, Kendall rank correlation, Spearman we observed trend low-frequency parts are main drivers markets’ fluctuations. The low-frequencies caused by special events. In nutshell, affected economic development rather than short-lived variations ordinary disequilibrium supply-demand.