Bayesian model choice and infection route modelling in an outbreak of Norovirus

Abstract

A data set from an outbreak of gastroenteritis in a school is analysed using a stochastic transmission model. The causative agent of the outbreak is believed to be a Norovirus, spread through person-to-person contact. Particular attention is given to the question of whether or not vomiting episodes enhance the spread of the virus via aerosol transmission. The methodology developed uses Bayesian model choice, implemented with reversible-jump Markov chain Monte Carlo methods. The methodology appears to be highly sensitive to assumptions made concerning the data, which provides some assurance that the conclusions are driven by observations rather than the underlying model and methodology.