A full investigation of the directional congestion in data envelopment analysis

Somayeh Khezri, Akram Dehnokhalaji, Farhad Hosseinzadeh Lotfi

Research output: Contribution to journalArticle

Abstract

One of interesting subjects in Data Envelopment Analysis (DEA)
is estimation of congestion of Decision Making Units (DMUs). Con-
gestion is evidenced when decreases (increases) in some inputs result in
increases (decreases) in some outputs without worsening (improving)
any other input/output. Most of the existing methods for measuring
the congestion of DMUs utilize the traditional denition of congestion
and assume that inputs and outputs change with the same proportion.
Therefore, the important question that arises is whether congestion
will occur or not if the decision maker (DM) increases or decreases
the inputs dis-proportionally. This means that, the traditional deni-
tion of congestion in DEA may be unable to measure the congestion
of units with multiple inputs and outputs. This paper focuses on the
directional congestion and proposes methods for recognizing the di-
rectional congestion using DEA models. To do this, we consider two
dierent scenarios: (i) just the input direction is available. (ii) none
of the input and output directions are available. For each scenario,
we propose a method consists in systems of inequalities or linear pro-
gramming problems for estimation of the directional congestion. The validity of the proposed methods are demonstrated utilizing two nu-
merical examples.
Original languageEnglish
JournalRAIRO - operations research
DOIs
Publication statusAccepted/In press - 18 Sep 2019

Fingerprint

Data envelopment analysis
Data Envelopment Analysis
Congestion
Decision making
Output
Unit
Decision Making
Decrease
Scenarios
Proportion

Bibliographical note

© 2019 EDP Sciences

Cite this

@article{584dee03545a47549122c11aedb78f9f,
title = "A full investigation of the directional congestion in data envelopment analysis",
abstract = "One of interesting subjects in Data Envelopment Analysis (DEA)is estimation of congestion of Decision Making Units (DMUs). Con-gestion is evidenced when decreases (increases) in some inputs result inincreases (decreases) in some outputs without worsening (improving)any other input/output. Most of the existing methods for measuringthe congestion of DMUs utilize the traditional denition of congestionand assume that inputs and outputs change with the same proportion.Therefore, the important question that arises is whether congestionwill occur or not if the decision maker (DM) increases or decreasesthe inputs dis-proportionally. This means that, the traditional deni-tion of congestion in DEA may be unable to measure the congestionof units with multiple inputs and outputs. This paper focuses on thedirectional congestion and proposes methods for recognizing the di-rectional congestion using DEA models. To do this, we consider twodierent scenarios: (i) just the input direction is available. (ii) noneof the input and output directions are available. For each scenario,we propose a method consists in systems of inequalities or linear pro-gramming problems for estimation of the directional congestion. The validity of the proposed methods are demonstrated utilizing two nu-merical examples.",
author = "Somayeh Khezri and Akram Dehnokhalaji and {Hosseinzadeh Lotfi}, Farhad",
note = "{\circledC} 2019 EDP Sciences",
year = "2019",
month = "9",
day = "18",
doi = "10.1051/ro/2019092",
language = "English",
journal = "RAIRO - operations research",
issn = "0399-0559",
publisher = "EDP Sciences",

}

A full investigation of the directional congestion in data envelopment analysis. / Khezri, Somayeh; Dehnokhalaji, Akram; Hosseinzadeh Lotfi, Farhad.

In: RAIRO - operations research, 18.09.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A full investigation of the directional congestion in data envelopment analysis

AU - Khezri, Somayeh

AU - Dehnokhalaji, Akram

AU - Hosseinzadeh Lotfi, Farhad

N1 - © 2019 EDP Sciences

PY - 2019/9/18

Y1 - 2019/9/18

N2 - One of interesting subjects in Data Envelopment Analysis (DEA)is estimation of congestion of Decision Making Units (DMUs). Con-gestion is evidenced when decreases (increases) in some inputs result inincreases (decreases) in some outputs without worsening (improving)any other input/output. Most of the existing methods for measuringthe congestion of DMUs utilize the traditional denition of congestionand assume that inputs and outputs change with the same proportion.Therefore, the important question that arises is whether congestionwill occur or not if the decision maker (DM) increases or decreasesthe inputs dis-proportionally. This means that, the traditional deni-tion of congestion in DEA may be unable to measure the congestionof units with multiple inputs and outputs. This paper focuses on thedirectional congestion and proposes methods for recognizing the di-rectional congestion using DEA models. To do this, we consider twodierent scenarios: (i) just the input direction is available. (ii) noneof the input and output directions are available. For each scenario,we propose a method consists in systems of inequalities or linear pro-gramming problems for estimation of the directional congestion. The validity of the proposed methods are demonstrated utilizing two nu-merical examples.

AB - One of interesting subjects in Data Envelopment Analysis (DEA)is estimation of congestion of Decision Making Units (DMUs). Con-gestion is evidenced when decreases (increases) in some inputs result inincreases (decreases) in some outputs without worsening (improving)any other input/output. Most of the existing methods for measuringthe congestion of DMUs utilize the traditional denition of congestionand assume that inputs and outputs change with the same proportion.Therefore, the important question that arises is whether congestionwill occur or not if the decision maker (DM) increases or decreasesthe inputs dis-proportionally. This means that, the traditional deni-tion of congestion in DEA may be unable to measure the congestionof units with multiple inputs and outputs. This paper focuses on thedirectional congestion and proposes methods for recognizing the di-rectional congestion using DEA models. To do this, we consider twodierent scenarios: (i) just the input direction is available. (ii) noneof the input and output directions are available. For each scenario,we propose a method consists in systems of inequalities or linear pro-gramming problems for estimation of the directional congestion. The validity of the proposed methods are demonstrated utilizing two nu-merical examples.

UR - https://www.rairo-ro.org/component/article?access=doi&doi=10.1051/ro/2019092

U2 - 10.1051/ro/2019092

DO - 10.1051/ro/2019092

M3 - Article

JO - RAIRO - operations research

JF - RAIRO - operations research

SN - 0399-0559

ER -