Methodology: Frontier Efficiency Measurement Techniques

Abstract

For the measurement of the technical or economic efficiency of decision-making units (DMUs; e.g. schools, hospitals, waste disposal companies, local governments, etc.) it is first necessary to define an appropriate set of input and output combinations. The inputs and outputs are then used to construct a best practice frontier - that is, a frontier which includes the most efficient decision-making units. Subsequently, the technical or economic efficiency of the other decision-making units lying below the best practice frontier can be determined by measuring the deviation from this frontier. Several problems, however, arise when one attempts to implement these two simple steps into real-world applications: Firstly, how the best practice frontier can be generated given a data set of DMUs, and secondly, after choosing an adequate method, identifying the extent to which deviations from the best practice frontier are attributable to either “real” inefficiencies or other influences such as measurement errors. These problems have been addressed in numerous different ways in the literature.