Modelling regional patterns of inefficiency: A Bayesian approach to geoadditive panel stochastic frontier analysis with an application to cereal production in England and Wales

We propose a flexible Bayesian approach to inefficiency modelling that accounts for regional patterns of local performance. The model allows for a separated treatment of individual heterogeneity and determinants of inefficiency. Regional dependence structures and location-specific unobserved spatial heterogeneity are modelled via geoadditive predictors in the inefficiency term of the stochastic frontier model. Inference becomes feasible through Markov chain Monte Carlo simulation techniques. In an empirical illustration we find that regional patterns of inefficiency characterize cereal production in England and Wales. Neglecting common performance patterns of farms located in the same region induces systematic biases to inefficiency estimates. (C) 2019 Elsevier B.V. All rights reserved.