Generalised additive models (GAMs) assume that the mean of the dependent variable depends on an additive predictor through a nonlinear link function. GAMs permit the response probability distribution to be any member of the exponential family of distributions. For example, the non-linear link may be, for instance, Poisson or Gaussian in nature. This gives rise to methods such as Poisson regression modelling and loess smoothing, which are common in pidemiological studies on the association between temperature and mortality rates, for instance (Gouveia et al. 2003).