A0299
Title: Statistical inference for highly correlated stationary point processes and noisy bivariate Neyman-Scott processes
Authors: Takaaki Shiotani - Graduate School of Mathematical Sciences, The University of Tokyo (Japan) [presenting]
Abstract: Motivated by the task of estimating lead-lag relationships in high-frequency financial data, the focus is on how to infer highly correlated structures between point processes using quasi-likelihood methods. High correlation refers to situations in which the correlogram diverges for certain parameter values, placing the problem outside the reach of existing asymptotic theory. An asymptotic framework is developed that is applicable under such conditions. As a concrete example, a noisy bivariate Neyman-Scott point process that can be employed for lead-lag estimation is treated.
