http://scholars.ntou.edu.tw/handle/123456789/21852
Title: | Integrating group frontier and metafrontier directional distance functions to evaluate the efficiency of production units | Authors: | Yu, Ming-Miin See, Kok Fong Hsiao, Bo |
Keywords: | CARBON EMISSION PERFORMANCE;TECHNOLOGY GAPS;TECHNICAL EFFICIENCY;ENERGY EFFICIENCY;WATER COMPANIES;DEA APPROACH | Issue Date: | 16-Aug-2022 | Publisher: | ELSEVIER | Journal Volume: | 301 | Journal Issue: | 1 | Start page/Pages: | 254-276 | Source: | EUR J OPER RES | Abstract: | Over the last decade, many studies have adopted the data envelopment analysis (DEA)-type metafrontier framework to relax the constraint of technological heterogeneity. In conventional metafrontier analyzes, either radial or nonradial DEA models are used in two separate DEA efficiency analyzes. The results of a metafrontier analysis may be biased if this approach is adopted in a nonradial DEA model. One possible problem is that the value of the technology gap ratio is greater than one because the technology gaps to be estimated for decision-making units (DMUs) under different technology groups relative to the metatechnology have no connection between group frontiers and metafrontiers. Furthermore, the direction of projection of each DMU onto the metafrontier is totally independent of the direction to the efficiency frontier of the respective group frontier. Our proposed integration of group technology and metatechnology constraints into a union model offers a possible solution to the existing metafrontier problem and provides more robust metafrontier results regardless of whether radial or nonradial DEA models are used. Four numerical examples and one empirical application are demonstrated, and the results appear to support the use of our proposed model.(c) 2021 Elsevier B.V. All rights reserved. |
URI: | http://scholars.ntou.edu.tw/handle/123456789/21852 | ISSN: | 0377-2217 | DOI: | 10.1016/j.ejor.2021.10.054 |
Appears in Collections: | 運輸科學系 07 AFFORDABLE & CLEAN ENERGY 12 RESPONSIBLE CONSUMPTION & PRODUCTION |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.