An Information Theoretic Approach to Flexible Stochastic Frontier Models

Parametric stochastic frontier models have a long history in applied production economics, but the class of tractible parametric models is relatively small. Consequently, researchers have recently considered non–parametric alternatives such as kernel density estimators, functional approximations, and data envelopment analysis (DEA). The purpose of this paper is to present an information theoretic approach to constructing more flexible classes of parametric stochastic frontier models. Further, the proposed class of models nests all of the commonly used parametric methods as special cases, and the proposed modeling framework provides a comprehensive means to conduct model specification tests. The modeling framework is also extended to develop information theoretic measures of mean technical efficiency and to construct a profile likelihood estimator of the stochastic frontier model.