During the last three decades, Bayesian methods have developed greatly in the field of epidemiology. Their main challenge focusses around computation, but the advent of Markov Chain Monte Carlo methods (MCMC) and in particular of the WinBUGS software has opened the doors of Bayesian modelling to the wide research community. However model complexity and database dimension still remain a constraint.Recently the use of Gaussian random fields has become increasingly popular in epidemiology as very often epidemiological data are characterised by a spatial and/or temporal structure which needs to be taken into account in the inferential process. The Integrated Nested Laplace Approximation (INLA) approach has been developed as a computationally efficient alternative to MCMC and the availability of an R package (R-INLA) allows researchers to easily apply this method.In this paper we review the INLA approach and present some applications on spatial and spatio-temporal data.
Bibliographical noteFunding Information:
The authors wish to thank Dr. Finn Lindgren for his help with the development of the R code implemented for the examples in Section 4 , and Dr. Léa Fortunato for her comments on Section 3.2–3.3 . Dr. Marta Blangiardo received partial support from the NERC-MRC Grant NE/I00789X/1 ; Dr. Gianluca Baio received partial support from the UK Department of Health’s NIHR Biomedical Research Centres funding scheme ; Dr. Michela Cameletti received partial support from the FYRE 2011 (Fostering Young REsearchers) project founded by Fondazione Cariplo and Universitá degli Studi di Bergamo .
- Area-level data
- Bayesian approach
- Integrated Nested Laplace Approximation
- Point-level data
- Stochastic Partial Differential Equation approach
ASJC Scopus subject areas
- Geography, Planning and Development
- Infectious Diseases
- Health, Toxicology and Mutagenesis