Global Pervasive Computational Epidemiology Seminar Series: David Higdon

Bayesian Model Calibration for Constraining Agent-Based Models

Speaker: David Higdon, Virginia Tech

Abstract: Agent-based models (ABMs) use rules at the individual (agent) level to simulate a social, ecologic, or social-technical system, producing structured behavior when viewed at an aggregated level. ABMs allow consideration of interactions, behaviors, outcomes, and interventions at a very fine resolution, giving them a connection to reality that is often missing from more aggregated modeling approaches. Of course, this comes with a price. For example, ABMs typically come with high computational costs, random realizations, and difficulty in capturing more aggregated properties of the real system. This talk will use a toy example to highlight the key concepts of Bayesian model calibration for constraining ABMs with observations; it'll also touch on Approximate Bayesian Computation (ABC). I'll then go on to show how such methodology can be used in more involved applications, using an ABM developed during the 2014 Ebola epidemic.

Bio: David M. Higdon is a professor in the Statistics Department at Virginia Tech. Previously, he spent 10 years as a scientist or group leader of the Statistical Sciences Group at Los Alamos National Laboratory. He is an expert in Bayesian statistical modeling of environmental and physical systems, combining physical observations with computer simulation models for prediction and inference. Dr. Higdon has served on several advisory groups concerned with statistical modeling and uncertainty quantification and co-chaired the NRC Committee on Mathematical Foundations of Validation, Verification, and Uncertainty Quantification. He is a Fellow of the American Statistical Association.

Join the webinar here.