Modelling the presence of disease under spatial misalignment using Bayesian latent Gaussian models

  • Xavier Barber Operational Research Centre, Miguel Hernández de Elche University, Elche, Spain.
  • David Conesa | conesa@uv.es Department of Statistics and Operational Research, University of Valencia, Valencia, Spain.
  • Silvia Lladosa Department of Statistics and Operational Research, University of Valencia, Valencia, Spain.
  • Antonio López-Quílez Department of Statistics and Operational Research, University of Valencia, Valencia, Spain.

Abstract

Modelling patterns of the spatial incidence of diseases using local environmental factors has been a growing problem in the last few years. Geostatistical models have become popular lately because they allow estimating and predicting the underlying disease risk and relating it with possible risk factors. Our approach to these models is based on the fact that the presence/absence of a disease can be expressed with a hierarchical Bayesian spatial model that incorporates the information provided by the geographical and environmental characteristics of the region of interest. Nevertheless, our main interest here is to tackle the misalignment problem arising when information about possible covariates are partially (or totally) different than those of the observed locations and those in which we want to predict. As a result, we present two different models depending on the fact that there is uncertainty on the covariates or not. In both cases, Bayesian inference on the parameters and prediction of presence/absence in new locations are made by considering the model as a latent Gaussian model, which allows the use of the integrated nested Laplace approximation. In particular, the spatial effect is implemented with the stochastic partial differential equation approach. The methodology is evaluated on the presence of the Fasciola hepatica in Galicia, a North-West region of Spain.

Dimensions

Altmetric

PlumX Metrics

Downloads

Download data is not yet available.
Published
2016-04-18
Info
Issue
Section
Original Articles
Keywords:
Bayesian Kriging, Fasciola hepatica, Geostatistics, INLA, Hierarchical Bayesian modelling
Statistics
  • Abstract views: 2565

  • PDF: 1138
  • HTML: 2145
How to Cite
Barber, X., Conesa, D., Lladosa, S., & López-Quílez, A. (2016). Modelling the presence of disease under spatial misalignment using Bayesian latent Gaussian models. Geospatial Health, 11(1). https://doi.org/10.4081/gh.2016.415