EFFICIENCY MEASUREMENT WITH MULTIPLE OUTPUTS AND MULTIPLE INPUTS

This paper discusses modeling technical and allocative inefficiencies in both cost minimizing and profit maximizing frameworks with special emphasis on multiple inputs and multiple outputs. Both primal and dual models are considered for this purpose. In the primal approach we use a separable output and input function (the constant elasticity of tra nsformation output function and Cobb-Douglas input function). The dual models assume translog cost or profit functions. Technical inefficien cy is assumed to be random in the cross-sectional models, and fixed fi rm-specific parameter in the panel data models. Allocative inefficienc ies are always treated as parameters. We derive exact relations linkin g technical inefficiency and allocative inefficiencies to cost and pro fit when the underlying technology is represented by a flexible functi onal form such as the translog. It is shown that appending a one-sided homoscedastic error term to model technical inefficiency, or neglecti ng technical inefficiency altogether in a translog profit tunciton res ults in model misspecification and inconsistent parameter estimates.