运筹与管理 ›› 2017, Vol. 26 ›› Issue (11): 65-69.DOI: 10.12005/orms.2017.0261

• 理论分析与方法探讨 • 上一篇    下一篇

一种基于虚拟决策单元的排序方法的完善和扩展

韩伟一   

  1. 哈尔滨工业大学 经济与管理学院,黑龙江 哈尔滨 150001;
  • 收稿日期:2015-11-12 出版日期:2017-11-25
  • 作者简介:韩伟一(1974-),男,山西高平人,副教授,博士,研究方向:数学规划、组合优化。
  • 基金资助:
    国家自然科学基金资助项目(71401046);中央高校基本科研业务费专项资金资助(HIT.HSS.201406)

Perfection and Extension of a Ranking Method Based on the Virtual Decision-making Unit

HAN Wei-yi   

  1. School of Economic and Management, Harbin Institute of Technology, Harbin 150001, China;
  • Received:2015-11-12 Online:2017-11-25

摘要: 本文对文[1]中提出的基于虚拟决策单元的排序方法进行了完善和扩展。首先,根据CCR模型,给出了两类特殊的DEA模型,分别是仅有投入数据的DEA模型和仅有产出数据的DEA模型;其次,基于这两个模型,应用上述方法实现了对仅有投入(或产出)数据的决策单元的排序;第三,给出了排序方法中参数a的计算方法;最后,通过修正排序模型,有效提高了排序方法的计算精度。改进后的排序方法避免了两个决策单元因为相对效率值过小而不能排序的情形,其应用范围也进一步扩大。

关键词: 运筹学, 数据包络分析, 排序方法, 决策单元排序, 虚拟决策单元

Abstract: In the paper, a ranking method based on the virtual decision-making unit is perfected and extended, which is developed in[1]. Firstly, according to CCR model, two special models are presented, which are DEA model only with input data and DEA model only with output data. Secondly, based on these two models, decision-making units only with input data or output data can be ranked by applying the mentioned-above method. Thirdly, the computational method of parameter a is given. Finally, the calculation accuracy of ranking method is improved efficiently by modifying ranking models. As a result, the improved method can avoid the situation, in which two decision-making units can’t be ranked as their relative efficiency values are very small. Furthermore, its application range is enlarged.

Key words: operations research, data envelopment analysis, ranking method, ranking decision-making units, virtue decision-making unit

中图分类号: