Structural and behavioral robustness in applied best-practice regulation

• DEA is widely used in network regulation to inform regulators on cost-efficiency.
• In regulation the model needs robustness for data errors and misreporting.
• We analyze the methods used in practice in Germany and Sweden.
• The most adapted methods are influence based, in particular super-efficiency.

Benchmarking methods, primarily non-parametric techniques such as Data Envelopment Analysis, have become well-established and informative tools for economic regulation, in particular in energy infrastructure regulation. The axiomatic features of the non-parametric methods correspond closely to the procedural and economic criteria for good practice network regulation. However, critique has been voiced against the robustness of best-practice regulation in presence of uncertainty regarding model specification, data definition and collection. Incorrect data may result from structural sources, such as heterogeneous technologies; deterministic approaches applied to stochastic data generation processes or poorly defined scope of activity. Specifically within regulation, reporting may also be biased through individual gaming or collusive behavior, including the intentional provision of absurd data in order to stall or perturb regulatory process (here called maverick reporting). We review three families of outlier detection methods in terms of their function and application using a data set from Swedish electricity distribution, illustrating the different types of outliers, contrasting with the actual analysis ex post. This paper investigates the foundation of the critique both conceptually and by describing the actual state-of-the-art used in energy network regulation using frontier analysis models in Sweden (2000–2003) and in Germany (2007-). Finally, the paper concludes on the role of outlier detection as a mean to implement regulation with higher robustness.