Spatial Mathematical Analysis: An Application to Mapping of Dengue Hemorrhagic Fever in Thailand
A generalized linear mixed model (GLMM) with spatial random effects for spatial data is proposed. The random
effects are assumed to be normally distributed and the spatial random effects are assumed to be a proper conditional
autoregressive (proper CAR) model. A hierarchical Bayesian method is used for parameter estimation. The proposed model
is applied to dengue hemorrhagic fever (DHF) data in Thailand. Seasons and some climatic covariates, rainfall and
temperature, are also considered. The DHF maps are constructed from the posterior means of the morbidity rates.
Keywords- Dengue hemorrhagic fever (DHF) mapping, Generalized linear mixed model (GLMM), Proper Conditional
autoregressive model (proper CAR), Spatial random effects