Stochastic frontier analysis using Stata

This paper describes sfcross and sfpanel, two new Stata commands for the estimation of cross-sectional and panel data stochastic frontier models. sfcross extends the official frontier capabilities by including additional models (Greene 2003; Wang 2002) and command functionality, such as the possibility to manage complex survey data characteristics. Similarly, sfpanel allows to estimate a much wider range of time-varying inefficiency models compared to the official xtfrontier command including, among the others, the Cornwell et al. (1990) and Lee and Schmidt (1993) models, the exible model of Kumbhakar (1990), the inefficiency effects model of Battese and Coelli (1995) and the "true" fixed and random-effects models developed by Greene (2005a). A brief overview of the stochastic frontier literature and a description of the two commands and their options are given, and illustrations using simulated and real data are provided.