Backpropagation Neural Network versus Translog Model in Stochastic Frontiers: a Note Carlo Compatrison.

Little attention has been given to the effects of functional form mis-specification on the estimation of stochastic frontier models and to the possibility of using backpropagation neural netwok as a flexible functional form to approximate the production or cost functions. This paper has two main aims. First, it uses Monte Carlo experimentation to investigate the effects of functional form mis-specification on the finite sample properties of the maximum likelihod (ML) estimators of the half-normal stochastic frontier production functions; second it compared the performance of backpropagation neural network with that of translog.