Estimating Efficiency Effects in a Panel Data Stochastic Frontier Model

This paper proposes a stochastic frontier model which includes time-invariant unobserved heterogeneity along with the efficiency effects. The efficiency effects are specified by a standard normal cumulative distribution function of exogenous variables which ensures the efficiency scores to lie in a unit interval. The model parameters are consistently estimated by non-linear least squares after removing the individual effects by the usual within transformation. The efficiency scores are directly calculated once the model is estimated. An empirical illustration based on widely used panel data on Indian farmers is presented.