Identifying efficient regulated firms with unobserved technological heterogeneity: A nested latent class approach to Norwegian electricity distribution networks

Since the 1990s, electricity distribution networks in many countries have been subject to incentive regulation. The sector regulators aim to identify the best performing utilities as “reference or frontier firms” in order to determine their relative efficiency of other firms. This paper develops a nested latent class (NLC) model approach where unobserved differences in performance are modeled using two ‘zero inefficiency stochastic frontier’ (ZISF) models nested in a ‘latent class stochastic frontier’ (LCSF) model. This is in order to capture the unobserved differences due to technology or environmental conditions. This model allows researchers and regulators to identify reference networks that are persistently 100% efficient when the underlying technology is heterogeneous. We illustrate the proposed model with an application to the Norwegian distribution network utilities for the period 2004-2011. We find that the efficiency scores in both LCSF and ZISF models are biased, and some firms in the ZISF model are wrongly labelled as inefficient. Conversely, inefficient firms can be wrongly labelled as being fully efficient by the ZISF model.