Title: Network quantile autoregression
Authors: Weining Wang - City U of London (United Kingdom) [presenting]
Abstract: It is a challenging task to understand the complex dependency structures in a ultra-high dimensional network, especially when the dependency between some of the nodes are highly non-linear. To tackle this problem, we consider a network quantile autoregression model (NQAR) to model the dynamic tail behavior ina complex system. In particular, we relate responses to its connected nodes and node specific characteristics in a quantile autoregression process. A minimum contrast estimation approach for the NQAR model is introduced, and its asymptotic properties are studied. Finally, we demonstrate the usage of our model by studying the financial contagions in Chinese stock market accounting for shared ownership of companies.