When, where and how to estimate persistent and transient efficiency in stochastic frontier panel data models

• Four-component panel data stochastic frontier model.
• The model distinguishes between long- and short-run inefficiency.
• The model accounts for unobserved heterogeneity.
• Finite sample properties of the estimator.
• Real-data examples and guide for practitioners.

In this paper we examine robustness of a recently developed panel data stochastic frontier model that allows for both persistent and transient (also known as long-run and short-run or time-invariant and time-varying) inefficiency along with random firm-effects (heterogeneity) and noise. We address some concerns that the practitioners might have about this model. First, given that there are two random time-invariant components (persistent inefficiency and firm-effects) the concern is whether the model can accurately identify them, and if so how precisely can the model estimate them? Second, there are two time-varying random components (transient inefficiency and noise), and the concern is whether the model can separate noise from transient inefficiency, and if so how precisely can the model estimate transient inefficiency? Third, how well are persistent and transient inefficiency estimated under different scenarios, viz., under different configurations of the variance parameters of the four random components? Given that the model is quite complex, relatively new and becoming quite popular in the panel efficiency literature, we feel that there is need for a detailed simulation study to examine when, where and how one can use this model with confidence to estimate persistent and transient inefficiency.