Online Program Home
  My Program

All Times EDT

Abstract Details

Activity Number: 9 - Bayesian Data Science: The New Frontier
Type: Invited
Date/Time: Monday, August 3, 2020 : 10:00 AM to 11:50 AM
Sponsor: Section on Bayesian Statistical Science
Abstract #308152
Title: Bayesian Nonparametric Modeling for Hawkes Processes
Author(s): Athanasios Kottas* and Hyotae Kim
Companies: University of California, Santa Cruz and University of California, Santa Cruz
Keywords: Bayesian nonparametrics; Earthquake modeling; Erlang mixtures; Gamma process; Marked point processes; Markov chain Monte Carlo
Abstract:

We will present a nonparametric Bayesian modeling framework for Hawkes processes. The objective is to increase the inferential scope for this practically important class of point processes by exploring flexible models for its conditional intensity function. In particular, we develop different types of prior models for the immigrant intensity and for the offspring  density, the two functions that define the Hawkes process conditional intensity. The prior models are carefully constructed such that, along with the Hawkes process branching structure, they enable handling efficiently the complex likelihood normalizing terms in implementation of inference. The methods will be explored for earthquake modeling, a key application area for Hawkes processes. In the context of this application area, we will discuss extensions of the nonparametric Bayesian models to incorporate information on mark variables (such as earthquake magnitude), as well as to study modeling and inference for space-time Hawkes processes.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2020 program