Efficiency Decomposition of the Multi-Stage Network Dea in Variable Returns to Scale: an Additive Dissection

View Statistics Email Alert RSS Feed

Information

Details

Project title

Code/計畫編號

MOST109-2410-H019-004

Translated Name/計畫中文名

變動規模報酬下多階段網路DEA之效率分解：一種加法剖析

Project Coordinator/計畫主持人

Hsuan-Shih Lee

Funding Organization/主管機關

National Science and Technology Council

Department/Unit

Department of Shipping and Transportation Management

Website

https://www.grb.gov.tw/search/planDetail?id=13530896

Year

2020

Start date/計畫起

01-08-2020

Expected Completion/計畫迄

31-07-2021

Bugetid/研究經費

480千元

ResearchField/研究領域

工業工程

Kao and Hwang 在2008年提出了一個固定規模報酬乘數型式的兩階段網路模型。他們的模型是假設系統的效率是兩階段效率的乘積，換言之系統是以乘積的方式在運行。另一種方式，我們可以定義損失等於整合之投入(成本)減去整合之產出(收益)。建基於損失的概念，我們可以對系統如下剖析，系統的損失等於個別流程(子系統)的損失的總和。換言之，系統是以加法的方式在運行。我們發現，Kao and Hwang (2008)的模型也可以這樣去分析。以這個方式去分析系統，我們進一步可以發展出變動規模報酬乘數形式的兩階段模型，其對偶正好是Kao and Hwang (2008) 包络型式模型的擴展。建基於損失的概念，我們也發出不同於比率值效率的效率定義，同時我們也將兩階段變動規模乘數型式模型擴展至一般網路結構。Kao and Hwang (2008) proposed a model based on multiplier form for two-stage network under constant returns to scale. Their model assumes that the system efficiency is the product of the efficiencies of the two stages. That is, the system operates in a multiplicative way. Alternatively, we define loss to be equal to the aggregated input (cost) minus the aggregated output (revenue). Based the on the notion of the loss, we dissect the system in the way that the system loss is the sum of the losses of the subsystems. That is, a system operates in an additive way. We find that the model in [9] can be decomposed in this additive way. We further develop the multiplier form under VRS for the two-stage network based on losses, whose dual form is an extension of the envelopment of the CRS model in (2008). Based on losses, an alternative definition of efficiency other than ratio efficiency is provided. Based on additivity of losses, the two-stage VRS model is further extended to a general network structure.

Keyword(s)

資料包络分析
乘數型式
網路DEA
變動規模報酬
Data envelopment analysis (DEA)
Multiplier form
Network DEA
Variable returns to scale

DSpace CRIS

Efficiency Decomposition of the Multi-Stage Network Dea in Variable Returns to Scale: an Additive Dissection

Details

Description