Calibrating a Stochastic Agent Based Model Using Quantile-based Emulation

TL;DR

This paper introduces a Bayesian calibration method for stochastic agent-based epidemic models using quantile-based emulation, effectively handling multivariate outputs like infection time series.

Contribution

It extends quantile Gaussian process emulation within a Bayesian framework to calibrate complex stochastic models with multivariate outputs.

Findings

Successfully calibrated an Ebola epidemic model example.

Extended emulation approach to multivariate, time-series outputs.

Demonstrated effectiveness in a real-world epidemic simulation.

Abstract

In a number of cases, the Quantile Gaussian Process (QGP) has proven effective in emulating stochastic, univariate computer model output (Plumlee and Tuo, 2014). In this paper, we develop an approach that uses this emulation approach within a Bayesian model calibration framework to calibrate an agent-based model of an epidemic. In addition, this approach is extended to handle the multivariate nature of the model output, which gives a time series of the count of infected individuals. The basic modeling approach is adapted from Higdon et al. (2008), using a basis representation to capture the multivariate model output. The approach is motivated with an example taken from the 2015 Ebola Challenge workshop which simulated an ebola epidemic to evaluate methodology.