Endogeneity in panel data stochastic frontier model with determinants of persistent and transient inefficiency

Abstract

In this paper we consider a stochastic frontier panel data model in which the random firm-effects are introduced along with the persistent and transient technical inefficiency. Moreover, we allow determinants of both persistent and transient inefficiency, and allow both firm-effects and persistent inefficiency to be correlated with the regressors. We discuss a two-step procedure, which applies the MLE and the system NLS approach, to estimate parameters of the model and prediction of persistent and transient technical efficiency. Finally, we demonstrate our approach by applying it to the U.S. power generating plant data.