Selecting data envelopment analysis specifications and ranking units via principal component analysis

Data envelopment analysis (DEA) model selection is problematic. The estimated efficiency for any DMU depends on the inputs and outputs included in the model. It also depends on the number of outputs plus inputs. It is clearly important to select parsimonious specifications and to avoid as far as possible models that assign full high-efficiency ratings to DMUs that operate in unusual ways (mavericks). A new method for model selection is proposed in this paper. Efficiencies are calculated for all possible DEA model specifications. The results are analysed using Principal Component Analysis. It is shown that model equivalence or dissimilarity can be easily assessed using this approach. The reasons why particular DMUs achieve a certain level of efficiency with a given model specification become clear. The methodology has the additional advantage of producing DMU rankings. These rankings can always be established independently of whether the model is estimated under constant or under variable returns to scale.