On the generation of a regular multi-input multi-output technology using parametric output distance functions

Monte-Carlo experimentation is a well-known approach to test the performance of alternative methodologies under different hypothesis. In the frontier analysis framework, whatever parametric or non-parametric methods tested, most experiments have been developed up to now assuming single output multi-input production functions and data generated using a Cobb- Douglas technology. The aim of this paper is to show how reliable multi-output multi-input production data can be generated using a parametric output distance function approach. A flexible translog technology is used for this purpose that satisfies regularity conditions. Two meaningful outcomes of this analysis are the identification of a valid range of parameters values satisfying monotonicity and curvature restrictions and of a rule of thumb to be applied in empirical studies.