Cost efficiency analysis based on the DEA and StoNED models : case of Norwegian electricity distribution companies

摘要

Our paper applies data envelopment analysis (DEA)and stochastic non-parametric envelopment of data (StoNED) tomeasure cost efficiency of electricity distribution companies. Thedata cover 123 Norwegian electricity distribution companiesduring 2004-2010, and the performance of these companies iscompared across the two models with and withoutenvironmental variables, i.e., variables that account for localconditions that affect the companies’ costs. The results indicatethat the cost efficiency estimates with the StoNED approach aremuch higher than with the DEA method when we do notconsider environmental variables. It shows that the choice ofestimation methods is important with respect to the estimatedimpact of environmental variables on the performance. Inaddition, the inclusion of the environmental variables hasconsiderable effect on the classification of companies withrespect to local returns to scale.