Modified classification and regression tree splitting criteria for data with interactions

Bremner, A.P. and Taplin, R.H. (2002) Modified classification and regression tree splitting criteria for data with interactions. Australian & New Zealand Journal of Statistics, 44 (2). pp. 169-176.

Abstract

This paper proposes modified splitting criteria for classification and regression trees by modifying the definition of the deviance. The modified deviance is based on local averaging instead of global averaging and is more successful at modelling data with interactions. The paper shows that the modified criteria result in much simpler trees for pure interaction data (no main effects) and can produce trees with fewer errors and lower residual mean deviances than those produced by Clark & Pregibon’s (1992) method when applied to real datasets with strong interaction effects.

Item Type:	Journal Article
Publisher:	Blackwell Publishing Inc.
Copyright:	© Australian Statistical Publishing Association Inc. 2002.
URI:	http://researchrepository.murdoch.edu.au/id/eprint/34389

Item Control Page