Paper detail

A note on basis dimension selection in generalized additive modelling

Two new approaches for checking the dimension of the basis functions when using penalized regression smoothers are presented. The first approach is a test for adequacy of the basis dimension based on an estimate of the residual variance calculated by differencing residuals that are neighbours according to the smooth covariates. The second approach is based on estimated degrees of freedom for a smooth of the model residuals with respect to the model covariates. In comparison with basis dimension selection algorithms based on smoothness selection criterion (GCV, AIC, REML) the above procedures are computationally efficient enough for routine use as part of model checking.