Stochastic Frontier Models With Correlated Error Components

In the productivity modelling literature, the disturbances U (representing technical inefficiency) and V (representing noise) of the composite error W=V-U of the stochastic frontier model are assumed to be independent random variables. By employing the copula approach to statistical modelling, the joint behaviour of U and V can be parameterised thereby allowing the data the opportunity to determine the adequacy of the independence assumption. In this context, three examples of the copula approach are given: the first is algebraic (the Logistic-Exponential stochastic frontier model with margins bound by the Fairlie-Gumbel-Morgenstern copula) and the second and third are empirically oriented, using data sets well-known in productivity analysis. Analysed are a cross-section of cost data sampled from the US electrical power industry, and an unbalanced panel of data sampled from the US airline industry