Proposal of Efficiency Evaluation Method in Generalized Data Envelopment Analysis

Abstract

Data Envelopment Analysis (DEA) is one of methods to evaluate a relative efficiency of decision-making units (DMUs) with multiple inputs and outputs in production systems. The CCR, BCC and FDH model are well-known as a fundamental and representative DEA. Efficiency values in those conventional DEA models are estimated by the ratio of distance to so-called efficient frontier which is determined under a specific value judgement of decision maker. On the other hand, GDEA model evaluates the efficiency of taking account of various value judgements, and thus treats the exisiting DEA models in a unified way by adjusting a parameter α. However, the scale of GDEA-efficiency values is associated with the parameter, which yeileds that GDEA-efficiency values obtained under different α are not comparable. In this research, therefore, we try to propose a new evaluation method that provides standardized efficiency values in GDEA model, and also compare the proposed evaluation method with the conventional models including GDEA model through some data sets.