RANDOMIZING EFFICIENCY SCORES IN DEA USING BETA DISTRIBUTION UNDER ‘UNIFORM SAMPLING’ OF ASSURANCE REGIONS

摘要

A criticism leveled against Data Envelopment Analysis (DEA) is that it is incapable of handling input/output data contaminated with random errors, and therefore, efficiency scores reported by DEA may not be realistic. In the past, several researchers have addressed this issue by proposing Stochastic DEA models, where they treated inputs and outputs as random variables that follow probability distributions. In this paper, we propose a method to randomize efficiency scores by treating each score as an ‘order statistic’ of an underlying Beta distribution. We use Thompson et al.’s (1996) DEA model appended with Assurance Regions (AR) randomized by our ‘uniform sampling’. In an application to a set of banks, we demonstrate this method and derive some statistical results.