CMStatistics 2023: Start Registration
View Submission - CMStatistics
B1299
Title: High-frequency estimation of Ito semi martingale baseline for Hawkes processes Authors:  Olivier Scaillet - University of Geneva and Swiss Finance Institute (Switzerland)
Seunghyeon Yu - KAIST (Korea, South)
Yoann Potiron - Keio University (Japan) [presenting]
Abstract: Hawkes self-exciting processes are considered with a baseline driven by an Ito semi-martingale with possible jumps. When the kernel satisfies the short-range condition, and under in-fill, asymptotic, feasible statistics induced by central limit theory for empirical average and variance of local Poisson estimates are characterized. As a byproduct, a test for the absence of a Hawkes component and a test for baseline constancy are developed. Simulation studies corroborate the asymptotic theory. An empirical application on high-frequency data of the E-mini S\&P500 future contracts shows that the absence of a Hawkes component is always rejected while baseline constancy is frequently rejected.