Title: Simultaneous event multivariate point process models with application to causality analysis of financial markets
Authors: Daisuke Kurisu - Tokyo Institute of Technology (Japan) [presenting]
Naoto Kunitomo - University of Tokyo (Japan)
Abstract: In economic financial time series, big events are sometimes observed which are relatively rare, but often have significant influences, not only on a financial market, but also on several different markets and macro economics. By using simultaneous event Hawkes type models, which allows co-jumps, we analyze the causal effects of big events in the sense of the Granger-non- causality. In our data analysis, we investigate the causality among the financial markets of Tokyo, New York, London and other markets. We have found several important findings among financial markets.