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

Submitted: 24 September 2015
Accepted: 24 September 2015
Published: 18 April 2016
Abstract Views: 3160
PDF: 1478
HTML: 2217
Publisher's note
All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.

Authors

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.

Citations

Supporting Agencies

Ministerio de Economía y Competitividad (the Spanish Ministry of Economy and Finance) via research grant MTM2013- 42323-P (jointly financed with the European Regional Development Fund)

How to Cite

Barber, X., Conesa, D., Lladosa, S., & Lòpez-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

List of Cited By :

Crossref logo