Testing over-representation of observations in subsets of a DEA technology

Mette Asmild; Jens Leth Hougaard; Ole Bent Olesen

doi:10.1016/j.ejor.2013.03.038

Testing over-representation of observations in subsets of a DEA technology

Mette Asmild, Jens Leth Hougaard, Ole Bent Olesen

Sektion for Produktion, Markeder og Politik

1 Citationer (Scopus)

Abstract

This paper proposes a test for whether data are over-represented in a given production zone, i.e. a subset of a production possibility set which has been estimated using the non-parametric Data Envelopment Analysis (DEA) approach. A binomial test is used that relates the number of observations inside such a zone to a discrete probability weighted relative volume of that zone. A Monte Carlo simulation illustrates the performance of the proposed test statistic and provides good estimation of both facet probabilities and the assumed common inefficiency distribution in a three dimensional input space. Potential applications include tests for whether benchmark units dominate more (or less) observations than expected.

Originalsprog	Engelsk
Tidsskrift	European Journal of Operational Research
Vol/bind	230
Udgave nummer	1
Sider (fra-til)	88-96
Antal sider	9
ISSN	0377-2217
DOI	https://doi.org/10.1016/j.ejor.2013.03.038
Status	Udgivet - 1 okt. 2013

Adgang til dokumentet

10.1016/j.ejor.2013.03.038

Citationsformater

@article{b28cd00f36db4624ac68487406af66bc,

title = "Testing over-representation of observations in subsets of a DEA technology",

abstract = "This paper proposes a test for whether data are over-represented in a given production zone, i.e. a subset of a production possibility set which has been estimated using the non-parametric Data Envelopment Analysis (DEA) approach. A binomial test is used that relates the number of observations inside such a zone to a discrete probability weighted relative volume of that zone. A Monte Carlo simulation illustrates the performance of the proposed test statistic and provides good estimation of both facet probabilities and the assumed common inefficiency distribution in a three dimensional input space. Potential applications include tests for whether benchmark units dominate more (or less) observations than expected.",

author = "Mette Asmild and Hougaard, {Jens Leth} and Olesen, {Ole Bent}",

year = "2013",

month = oct,

day = "1",

doi = "10.1016/j.ejor.2013.03.038",

language = "English",

volume = "230",

pages = "88--96",

journal = "European Journal of Operational Research",

issn = "0377-2217",

publisher = "Elsevier",

number = "1",

}

TY - JOUR

T1 - Testing over-representation of observations in subsets of a DEA technology

AU - Asmild, Mette

AU - Hougaard, Jens Leth

AU - Olesen, Ole Bent

PY - 2013/10/1

Y1 - 2013/10/1

N2 - This paper proposes a test for whether data are over-represented in a given production zone, i.e. a subset of a production possibility set which has been estimated using the non-parametric Data Envelopment Analysis (DEA) approach. A binomial test is used that relates the number of observations inside such a zone to a discrete probability weighted relative volume of that zone. A Monte Carlo simulation illustrates the performance of the proposed test statistic and provides good estimation of both facet probabilities and the assumed common inefficiency distribution in a three dimensional input space. Potential applications include tests for whether benchmark units dominate more (or less) observations than expected.

AB - This paper proposes a test for whether data are over-represented in a given production zone, i.e. a subset of a production possibility set which has been estimated using the non-parametric Data Envelopment Analysis (DEA) approach. A binomial test is used that relates the number of observations inside such a zone to a discrete probability weighted relative volume of that zone. A Monte Carlo simulation illustrates the performance of the proposed test statistic and provides good estimation of both facet probabilities and the assumed common inefficiency distribution in a three dimensional input space. Potential applications include tests for whether benchmark units dominate more (or less) observations than expected.

U2 - 10.1016/j.ejor.2013.03.038

DO - 10.1016/j.ejor.2013.03.038

M3 - Journal article

SN - 0377-2217

VL - 230

SP - 88

EP - 96

JO - European Journal of Operational Research

JF - European Journal of Operational Research

IS - 1

ER -