Extinction and quasi-stationarity for discrete-time, endemic SIS and SIR models

TL;DR

This paper analyzes stochastic discrete-time SIS and SIR disease models, revealing how the basic reproductive number influences extinction times and quasi-stationary distributions, with implications for understanding disease persistence and eradication.

Contribution

It provides a comprehensive analysis of extinction and quasi-stationarity in stochastic SIS and SIR models, including explicit formulas and conditions for convergence to endemic or disease-free states.

Findings

Mean extinction times grow exponentially with population size when R0>1

Quasi-stationary distributions concentrate near endemic equilibrium for large N

Extinction occurs in finite time with probability one for all R0 values

Abstract

Stochastic discrete-time SIS and SIR models of endemic diseases are introduced and analyzed. For the deterministic, mean-field model, the basic reproductive number $R_0$ determines their global dynamics. If $R_0\le 1$, then the frequency of infected individuals asymptotically converges to zero. If $R_0>1$, then the infectious class uniformly persists for all time; conditions for a globally stable, endemic equilibrium are given. In contrast, the infection goes extinct in finite time with probability one in the stochastic models for all $R_0$ values. To understand the length of the transient prior to extinction as well as the behavior of the transients, the quasi-stationary distributions and the associated mean time to extinction are analyzed using large deviation methods. When $R_0>1$, these mean times to extinction are shown to increase exponentially with the population size $N$. Moreover, as $N$ approaches $\infty$, the quasi-stationary distributions are supported by a compact set bounded away from extinction; sufficient conditions for convergence to a Dirac measure at the endemic equilibrium of the deterministic model are also given. In contrast, when $R_0<1$, the mean times to extinction are bounded above $1/(1-\alpha)$ where $\alpha<1$ is the geometric rate of decrease of the infection when rare; as $N$ approaches $\infty$, the quasi-stationary distributions converge to a Dirac measure at the disease-free equilibrium for the deterministic model. For several special cases, explicit formulas for approximating the quasi-stationary distribution and the associated mean extinction are given. These formulas illustrate how for arbitrarily small $R_0$ values, the mean time to extinction can be arbitrarily large, and how for arbitrarily large $R_0$ values, the mean time to extinction can be arbitrarily large.