Title: Causality in multivariate time series with mixed components
Authors: Wagner Barreto-Souza - King Abdullah University of Science and Technology (Saudi Arabia) [presenting]
Hernando Ombao - King Abdullah University of Science and Technology (KAUST) (Saudi Arabia)
Abstract: The Granger causality is investigated in a general class of multivariate time series models that allow for a wide range of mixed components including: non-negative, count, bounded, binary, and real-valued time series. We explore the asymptotic properties of the proposed Granger causality test. Simulated and real data analyses are presented to illustrate the potential for the practice of the developed methodology.