Efficiency analysis to incorporate interval-scale data

Akram Dehnokhalaji; Pekka J. Korhonen; Murat Köksalan; Nasim Nasrabadi; Jyrki Wallenius

doi:10.1016/j.ejor.2010.03.039

Efficiency analysis to incorporate interval-scale data

Akram Dehnokhalaji, Pekka J. Korhonen, Murat Köksalan, Nasim Nasrabadi, Jyrki Wallenius

Operations & Information Management

Research output: Contribution to journal › Article › peer-review

Abstract

We develop an approach to efficiency analysis to enable us to incorporate interval-scale data in addition to ratio-scale data. Our approach introduces a measure of inefficiency and identifies efficient units as is done in Data Envelopment Analysis. The basic idea in our approach is to find the “best” hyperplane separating the units that are better and worse than each unit. “Best” is defined in such a way that the number of not-better units is maximal. The efficiency measure is defined as a proportion of not-better units to all units. The results are invariant under a strictly increasing linear re-scaling of any input- or output-variables. Thus zeroes or negative values do not cause problems for the analysis. The approach is used to analyze the data of the research evaluation exercise recently carried out at the University of Joensuu, Finland.

Original language	English
Pages (from-to)	1116-1121
Journal	European Journal of Operational Research
Volume	207
Issue number	2
DOIs	https://doi.org/10.1016/j.ejor.2010.03.039
Publication status	Published - 1 Dec 2010

Access to Document

10.1016/j.ejor.2010.03.039

Cite this

@article{107bb7fad8c540039889f11d65839ce6,

title = "Efficiency analysis to incorporate interval-scale data",

abstract = "We develop an approach to efficiency analysis to enable us to incorporate interval-scale data in addition to ratio-scale data. Our approach introduces a measure of inefficiency and identifies efficient units as is done in Data Envelopment Analysis. The basic idea in our approach is to find the “best” hyperplane separating the units that are better and worse than each unit. “Best” is defined in such a way that the number of not-better units is maximal. The efficiency measure is defined as a proportion of not-better units to all units. The results are invariant under a strictly increasing linear re-scaling of any input- or output-variables. Thus zeroes or negative values do not cause problems for the analysis. The approach is used to analyze the data of the research evaluation exercise recently carried out at the University of Joensuu, Finland.",

author = "Akram Dehnokhalaji and Korhonen, {Pekka J.} and Murat K{\"o}ksalan and Nasim Nasrabadi and Jyrki Wallenius",

year = "2010",

month = dec,

day = "1",

doi = "10.1016/j.ejor.2010.03.039",

language = "English",

volume = "207",

pages = "1116--1121",

journal = "European Journal of Operational Research",

issn = "0377-2217",

publisher = "Elsevier",

number = "2",

}

TY - JOUR

T1 - Efficiency analysis to incorporate interval-scale data

AU - Dehnokhalaji, Akram

AU - Korhonen, Pekka J.

AU - Köksalan, Murat

AU - Nasrabadi, Nasim

AU - Wallenius, Jyrki

PY - 2010/12/1

Y1 - 2010/12/1

N2 - We develop an approach to efficiency analysis to enable us to incorporate interval-scale data in addition to ratio-scale data. Our approach introduces a measure of inefficiency and identifies efficient units as is done in Data Envelopment Analysis. The basic idea in our approach is to find the “best” hyperplane separating the units that are better and worse than each unit. “Best” is defined in such a way that the number of not-better units is maximal. The efficiency measure is defined as a proportion of not-better units to all units. The results are invariant under a strictly increasing linear re-scaling of any input- or output-variables. Thus zeroes or negative values do not cause problems for the analysis. The approach is used to analyze the data of the research evaluation exercise recently carried out at the University of Joensuu, Finland.

AB - We develop an approach to efficiency analysis to enable us to incorporate interval-scale data in addition to ratio-scale data. Our approach introduces a measure of inefficiency and identifies efficient units as is done in Data Envelopment Analysis. The basic idea in our approach is to find the “best” hyperplane separating the units that are better and worse than each unit. “Best” is defined in such a way that the number of not-better units is maximal. The efficiency measure is defined as a proportion of not-better units to all units. The results are invariant under a strictly increasing linear re-scaling of any input- or output-variables. Thus zeroes or negative values do not cause problems for the analysis. The approach is used to analyze the data of the research evaluation exercise recently carried out at the University of Joensuu, Finland.

UR - https://linkinghub.elsevier.com/retrieve/pii/S0377221710002663

U2 - 10.1016/j.ejor.2010.03.039

DO - 10.1016/j.ejor.2010.03.039

M3 - Article

SN - 0377-2217

VL - 207

SP - 1116

EP - 1121

JO - European Journal of Operational Research

JF - European Journal of Operational Research

IS - 2

ER -

Efficiency analysis to incorporate interval-scale data

Abstract

Access to Document

Other files and links

Fingerprint

Cite this