Title: Nonlinear dynamics and wavelet based analysis of crude oil prices
Authors: Emmanuel Senyo Fianu - Recent Affiliation--Leuphana University of Lueneburg (Germany) [presenting]
Abstract: A signal modality analysis is investigated for the characterization and the detection of nonlinearity in crude oil markets. Given the nonlinear and time-varying characteristics of international crude oil prices, this analysis employs the recently proposed delay vector variance (DVV) method, which examines local predictability of a signal in the phase space to detect the determinism and nonlinearity in the energy time series. In addition, wavelet transforms, which have recently emerged as a mathematical tool for multiresolution decomposition of signals, have been employed. In particular, a complex Morlet wavelet is used to detect and characterize the various phases of oil prices through the trajectory of its evolution. It has the potential applications in signalling processing that require variable time-frequency localizations. A detail overview of the feasibility of this methodology is highlighted. Our results aims at identifying the significant phases of the series and its relation to real-world phenomena in recent years as well future occurrences.