Abstract
This paper investigates the predictive ability of the Unites States (US) volatility risk index toward the European and Asian volatility risk indexes, and vice versa. We use the Hammerstein-ARX approach to model dependency between the different volatility risk indexes. The unknown parameters of the non-linear Hammerstein-ARX model are estimated using particle swarm optimization (PSO), in order to minimize the error between the real output and the forecasted output. Our empirical findings provide that the US implied volatility risk index is particularly powerful in forecasting the European and Asian volatility risk indexes than in the opposite case. We also show that the US implied volatility risk index react to other international implied volatility risk indexes linearly and non-linearly, and vice versa. The simulation results confirm the fitness and performance of the proposed PSO identification tool.
•We examine the forecasting of US volatility risk index toward other international volatility risk indexes, and vice versa.•The Hammerstein-ARX approach is used to forecast the implied volatility risk indexes (the Fear index) in financial markets.•Particle swarm optimization (PSO) is used to minimize the error between the real values and the forecasted values.•Significant forecasting power of US volatility risk index toward the European and Asian volatility risk indexes.•The accuracy of the proposed optimization tool is verified by performance criterions.