Bayesian inference in an extended SEIR model with nonparametric disease transmission rate: an application to the Ebola epidemic in Sierra Leone
- 20 June 2016
- journal article
- Published by Oxford University Press (OUP) in Biostatistics
- Vol. 17 (4), 779-792
- https://doi.org/10.1093/biostatistics/kxw027
Abstract
The 2014 Ebola outbreak in Sierra Leone is analyzed using a susceptible-exposed-infectious-removed (SEIR) epidemic compartmental model. The discrete time-stochastic model for the epidemic evolution is coupled to a set of ordinary differential equations describing the dynamics of the expected proportions of subjects in each epidemic state. The unknown parameters are estimated in a Bayesian framework by combining data on the number of new (laboratory confirmed) Ebola cases reported by the Ministry of Health and prior distributions for the transition rates elicited using information collected by the WHO during the follow-up of specific Ebola cases. The time-varying disease transmission rate is modeled in a flexible way using penalized B-splines. Our framework represents a valuable stochastic tool for the study of an epidemic dynamic even when only irregularly observed and possibly aggregated data are available. Simulations and the analysis of the 2014 Sierra Leone Ebola data highlight the merits of the proposed methodology. In particular, the flexible modeling of the disease transmission rate makes the estimation of the effective reproduction number robust to the misspecification of the initial epidemic states and to underreporting of the infectious cases.Keywords
This publication has 20 references indexed in Scilit:
- Estimating the Reproduction Number of Ebola Virus (EBOV) During the 2014 Outbreak in West AfricaPLoS Currents, 2014
- Modelling under-reporting in epidemicsJournal of Mathematical Biology, 2013
- Splines, knots, and penaltiesWIREs Computational Statistics, 2010
- Stochastic epidemic models: A surveyMathematical Biosciences, 2010
- The basic reproductive number of Ebola and the effects of public health measures: the cases of Congo and UgandaJournal of Theoretical Biology, 2004
- An Adaptive Metropolis AlgorithmBernoulli, 2001
- Transmission of Ebola Hemorrhagic Fever: A Study of Risk Factors in Family Members, Kikwit, Democratic Republic of the Congo, 1995The Journal of Infectious Diseases, 1999
- Flexible smoothing with B-splines and penaltiesStatistical Science, 1996
- On the definition and the computation of the basic reproduction ratio R 0 in models for infectious diseases in heterogeneous populationsJournal of Mathematical Biology, 1990
- Extra-Poisson Variation in Log-Linear ModelsJournal of the Royal Statistical Society Series C: Applied Statistics, 1984