Improving the identification of returns to scale in data envelopment analysis

In order to assess the efficiencies of a set of production units, it is nec essary to identify the nature of returns to scale which characterise effici ent production. Some methods have been developed to test the nature of the scale elasticity across the full range of scale sizes. However these tests are heavily weighted by the majority of the units and may not identify smal l ranges of scale size when different returns to scale hold. This paper dev elops a procedure based on a combination of Data Envelopment Analysis and r egression analysis to identify the ranges of scale size where the returns t o scale may differ from those in other ranges for the single-output, multi- input case. We also develop a measure of scale size across different input mixes.