Disease mapping in Germany Larynx cancer mortality count in Germany, 1986 to 1990 Spatial resolution: 544 regions For each region: Assume the data to be conditionally independent Poisson random variables: Linear predictor: i x i i i x i i μ : Intercept term : Linear effects of the level of smoking consumption covariate x i : Unstructured spatial effect, i.i.d. for each region i. i : Structured spatial effect, modelled as IGMRF. f ( ) : Helps defining non linear effects in the model specification. inla ( ) : Performs a Bayesian analysis of additive models as well as specify likelihood distribution. summary ( ) : Produces a summary of the main results from a fitted model. plot ( ) : Produces some plots from the fitted model.