Bayesian modelling of geostatistical malaria risk data

• Published in: Geospatial health Vol. 1; no. 1; pp. 127 - 139
• Main Authors: Gosoniu, L, Vounatsou, P, Sogoba, N, Smith, T
• Format: Journal Article
• Language: English; Italian
• Published: Italy PAGEPress Publications 01.11.2006
• Subjects: Bayes Theorem; Bayesian analysis; Geographic Information Systems - statistics & numerical data; Malaria; Malaria - epidemiology; Malaria - mortality; Malaria - prevention & control; Malaria - transmission; Mali - epidemiology; Markov Chains; Models, Statistical; Monte Carlo simulation; remote sensing, epidemiology, disease control, arthropod-borne viruses; Risk Assessment - statistics & numerical data; Mali
• ISSN: 1827-1987; 1970-7096
• DOI: 10.4081/gh.2006.287

Bayesian geostatistical models applied to malaria risk data quantify the environment-disease relations, identify significant environmental predictors of malaria transmission and provide model-based predictions of malaria risk together with their precision. These models are often based on the stationarity assumption which implies that spatial correlation is a function of distance between locations and independent of location. We relax this assumption and analyse malaria survey data in Mali using a Bayesian non-stationary model. Model fit and predictions are based on Markov chain Monte Carlo simulation methods. Model validation compares the predictive ability of the non-stationary model with the stationary analogue. Results indicate that the stationarity assumption is important because it influences the significance of environmental factors and the corresponding malaria risk maps.