Functions for Fitting Tree-Based Models

This paper describes a set of functions for tree-based modeling. Tree-based models provide an alternative to linear and additive models for regression and classification data. The models are fitted by binary recursive partitioning whereby a dataset is successively split into two subsets until it is feasible to continue. There are functions for growing, displaying, and interacting with tree-based models. This approach to tree-based models is consistent with the data-analytic approach to other models, and consists primarily of fits, residual analyses, and intense graphical inspection. The implementation, which is entirely in (NEW) S, consists of a set of S functions and several underlying C routines.