Effects of model specification, short-run, and long-run inefficiency: an empirical analysis of stochastic frontier models

Abstract

This paper examines the recent advances in stochastic frontier (SF) models and its implications for the performance of Norwegian crop-producing farms. In contrast to the previous studies, we used a cost function in multiple input-output frameworks to estimate both long-run (persistent) and short-run (transient) inefficiency. The empirical analysis is based on unbalanced farm-level panel data for 1991–2013 with 3 885 observations from 455 Norwegian farms specialising in crop production. We estimated seven SF panel data models grouped into four categories regarding the assumptions used to the nature of inefficiency. The estimated cost efficiency scores varied from 53–95%, showing that the results are sensitive to how the inefficiency is modeled and interpreted.