Since the 1990s, efficiency and benchmarking analysis has increasingly been used in network utilities research and regulation. A recurrent concern is the effect of observable environmental factors that are beyond the influence of firms and unobserved factors that are not identifiable on measured cost and quality performance of firms. This paper analyses the effect of observed geographic and weather factors and unobserved heterogeneity on a set of 128 Norwegian electricity distribution utilities for the 2001–2004 period. We utilise data on 78 geographic and weather variables to identify real economic inefficiency while controlling for observed and unobserved heterogeneity. We use the Factor Analysis technique to reduce the number of environmental factors into few composite variables and to avoid the problem of multicollinearity. In order to identify firm-specific inefficiency, we then estimate a pooled version of the established stochastic frontier model of Aigner et al. (1977) and the recent true random effects model of Greene (2004; 2005a,b) without and with environmental variables. The results indicate that the observed environmental factors have a rather limited influence on the utilities' average efficiency and the efficiency rankings. Moreover, the difference between the average efficiency scores and the efficiency rankings among the pooled and the true random effects models imply that the type of SFA model used is highly influencing the efficiency estimates.
- Input distance function
- Stochastic frontier analysis