Statistical inference for a partially observed interacting system of Hawkes processes

TL;DR

This paper develops statistical methods to estimate the probability parameter in a large, partially observed interacting system of Hawkes processes, considering different growth regimes of activity over time.

Contribution

It introduces asymptotic estimators for the interaction probability in a Hawkes process network under subcritical and supercritical growth conditions.

Findings

Estimator with convergence rate 1/√K in subcritical case

Estimator with convergence rate 1/√K + N/(m_t√K) in subcritical case

Estimator with convergence rate 1/√K + N/(m_t√K) in supercritical case

Abstract

We observe the actions of a $K$ sub-sample of $N$ individuals up to time $t$ for some large $K<N$. We model the relationships of individuals by i.i.d. Bernoulli($p$)-random variables, where $p\in (0,1]$ is an unknown parameter. The rate of action of each individual depends on some unknown parameter $\mu> 0$ and on the sum of some function $\phi$ of the ages of the actions of the individuals which influence him. The function $\phi$ is unknown but we assume it rapidly decays. The aim of this paper is to estimate the parameter $p$ asymptotically as $N\to \infty$, $K\to \infty$, and $t\to \infty$. Let $m_t$ be the average number of actions per individual up to time $t$. In the subcritical case, where $m_t$ increases linearly, we build an estimator of $p$ with the rate of convergence $\frac{1}{\sqrt{K}}+\frac{N}{m_t\sqrt{K}}+\frac{N}{K\sqrt{m_t}}$. In the supercritical case, where $m_{t}$ increases exponentially fast, we build an estimator of $p$ with the rate of convergence $\frac{1}{\sqrt{K}}+\frac{N}{m_{t}\sqrt{K}}$.