Inference in a stochastic SIR epidemic model using Bayesian filtering, Rennes, France, 4-8 July, 2016, pp.41-46.

We consider State Space Models (SSMs) as Discrete Time Markov
Chains (DTMC) to describe a stochastic SIR Epidemic dynamic. The unknown
static parameters are estimated by combining Sequential Monte Carlo and Markov
Chain Monte Carlo algorithms (SMC-within-MCMC) also known as Particle
Marginal Metropolis-Hastings (PMMH). The performances of the strategy are
evaluated using simulations. The method is illustrated by modeling the spread of
a viral infection in a small community.