Abstract
In this article, we carried out a comparative analysis of the efficiency results obtained using two existing approaches of DEA in relation to the methodology proposed here, which is an alternative to deal with differences of scale. For this, a study on the operational performance of the Brazilian air passenger transportation business is conducted. The proposal combines static clustering to the constant returns-to-scale model, and compensation scale differences among the clusters. The innovation relies on the adaption of a technique, originally designed to handle non-homogeneity to treat differences of scale. The results show that the proposed methodology increases the discrimination among companies, that is, some units that resulted 100% efficient in the existing approaches, had their efficiency reduced, resulting in less draws. Another relevant aspect is that the proposed methodology has comparative advantages over existing alternatives in the literature.
Key words:
data envelopment analysis; clustering; dynamic clusters; static clusters; air transportation
