Far out or alone in the crowd: Classification of selfevaluators in DEA

The units found strongly efficient in DEA studies on efficiency can be divided into self-evaluators and active peers, depending on whether the peers are referencing any inefficient units or not. The contribution of the paper starts with subdividing the selfevaluators into interior and exterior ones. The exterior self-evaluators are efficient “by default”; there is no firm evidence from observations for the classification. These units should therefore not been regarded as efficient, and be removed from the observations on efficiency scores when performing a two-stage analysis of explaining the distribution of the scores. A method for classifying self-evaluators based on the additive DEA model is developed. The application to municipal nursingand home care services of Norway shows significant effects of removing exterior self-evaluators from the data when doing a two-stage analysis.