Components of efficiency evaluation in data envelopment analysis

doi:10.1016/0377-2217(94)00131-U

European Journal of Operational Research

Volume 80, Issue 3, 2 February 1995, Pages 462-473

https://doi.org/10.1016/0377-2217(94)00131-U Get rights and content

Abstract

This paper examines three essential components which comprise efficiency evaluation in data envelopment analysis. The three components are present in each DEA model and determine the implicit evaluation scheme associated with the model. These components provide a framework for classifying the various DEA models with respect to (i) the form of envelopment surface, (ii) the orientation, and (iii) the pricing mechanism implicit in the multiplier lower bounds. The discussion focuses on the standard DEA models, includes additional issues relating to efficiency evaluation, and is illustrated by a computational example.

References (14)

T. Ahn et al.
A note on the efficiency characterizations obtained in different DEA models
Socio-Economic Planning Sciences
(1988)
A.I. Ali
Streamlined computation for data envelopment analysis
European Journal of Operational Research
(1993)
A. Charnes et al.
Measuring the efficiency of decision making units
European Journal of Operational Research
(1978)
A. Charnes et al.
Polyhedral cone-ratio DEA models with an illustrative application to large commercial banks
Journal of Econometrics
(1990)
A. Charnes et al.
Foundations of Data Envelopment Analysis for Pareto-Koopmans efficient empirical production functions
Journal of Econometrics
(1985)
L.M. Seiford et al.
Recent developments in DEA: The mathematical programming approach to frontier analysis
Journal of Econometrics
(1990)
T. Ahn et al.
Using data envelopment analysis to measure the efficiency of not-for-profit organizations: A critical evaluation — Comment
Managerial and Decision Economics
(1988)

There are more references available in the full text version of this article.

Cited by (92)

Eco-efficiency changes of the electricity and gas sectors across 28 European countries: A value-based data envelopment analysis productivity approach
2023, Socio-Economic Planning Sciences
This paper assesses the relative eco-efficiency changes in the electricity and gas sector (E&G)' production and consumption chains in 28 European countries. We propose a novel robustness assessment for the productivity index, specifically adjusted to value-based data envelopment analysis. Overall, results indicate that total factor productivity gains have been mainly driven by the catch-up effect across all chains of the E&G sector. When a more demanding perspective concerning negative environmental externalities is adopted, we find that the number of European countries that achieved productivity gains across all chains decreases. Besides, results depict the existence of lower productivity gains for the direct production chain when compared with the direct and indirect supply chains of the E&G sector. Germany, Luxembourg, and Belgium were consistently viewed as innovators across all chains, according to the environmental perspective. Several Eastern Europe countries usually viewed as policy laggards that resisted adopting the ambitious European decarbonization targets, showed total factor productivity gains in the supply chain of the E&G sector under a more environmental demanding perspective. Czechia was the only country with productivity losses across all chains, due to increasing coal-fired electricity generation in the time horizon assessed. The current partial return to coal as a source of electricity, due to the geopolitical tensions between Russia and Europe, brings additional challenges to the enhancement of the eco-efficiency of the European E&G sector.
Assessing the impact of COVID-19 on the efficiency of Portuguese state-owned enterprise hospitals
2022, Socio-Economic Planning Sciences
Citation Excerpt :
Finally, since the studies reviewed so far revealed that Portugal was unable to use its resources efficiently [2,28], we wanted to further understand which factors might help explain these findings, particularly considering the stringent resource allocation faced by Portuguese hospitals during the pandemic. The VBDEA model has been developed by [31] and tackles both the scaling bias and the absence of interpretation of the scores obtained through the weighted additive model [32]. This is accomplished by coupling into a single framework the DEA and MCDA approaches embedding the DMs’ preferences, also translating the input and output values into value scales.
This paper uses Value-Based Data Envelopment Analysis (VBDEA), to assess the impact of the COVID-19 pandemic on the efficiency of 37 state-owned enterprises (SOE) hospitals by employing data publicly available from the Portuguese Health Service database between January and November 2019 and 2020, respectively. Furthermore, a productivity index (specifically adjusted to the VBDEA approach) is also used that allows identifying which factors are behind the relative efficiency changes of these hospitals. The factors considered to perform the efficiency assessment of the Portuguese SOE hospitals include labour, capacity, and activity-related indicators. Out of the 37 SOE hospitals, 21 and 17 were efficient in 2019 and 2020, respectively. Irrespective of the value functions considered, the hospitals more often viewed as a reference for best practices were Santa Maria Maior, Tâmega e Sousa and Entre Douro e Vouga. Santa Maria Maior and Algarve were the only hospitals found to be robustly efficient for both years. Overall, the majority of SOE hospitals showed negative productivity (except for Évora and Santa Maria Maior) and all of them presented negative technological change, thus highlighting the massive impact that the COVID-19 outbreak has had on the performance of these hospitals. An additional conclusion is that inefficient hospitals substantially increased all their resources in 2020 as compared to inefficient hospitals in 2019, suggesting that the inefficiency of these hospitals was not due to the lack of resources. Finally, irrespective of the model employed, the hospitals located in the Portuguese northern region were more resilient to the COVID-19 crisis. All in all, to become more resilient (even for future COVID-19 outbreaks), hospitals should undertake changes that are advantageous irrespective of the obstacles they face and that are even beneficial during normal times. A culture of cooperation within and across hospitals should also be cultivated, which allows exchanging resources where they can be used more efficiently.
Efficiency of secondary schools in Ecuador: A value based DEA approach
2022, Socio-Economic Planning Sciences
This paper proposes a novel Value-Based Data Envelopment Analysis model which specifically tackles non-discretionary data to assess the performance of 159 secondary schools from Ecuador by employing data from the Programme for International Student Assessment for Development. When contrasted with traditional Data Envelopment Analysis models, the Value-Based Data Envelopment Analysis model has several innovative characteristics that can be particularly convenient not only for including the preferences (generally not incorporated) of the decision-makers, but because it easily handles negative or null data. In addition, this methodology also employs a procedure that allows performing the robustness assessment (rarely employed in similar studies) of the results obtained. The factors considered to perform the efficiency assessment of each school include indexes, which reflect the quality of both basic school infrastructures and instructional resources, the economic, social, and cultural level index of students, the student-teacher ratio, and test scores in maths, reading and science. Our findings suggest that the average efficient school has mean scores across all competencies below the average of Latin American and Caribbean countries. Besides, inefficient schools need to make a greater effort to improve results in maths when compared to reading and science competencies. Finally, it can be concluded that inefficient schools can improve students’ achievements by about 11%–12%, with almost the same instructional resources and with a ratio of students per teacher 23% higher but requiring an enhancement of the basic school infrastructure by about 7%.
Evaluating the efficiency of structural funds: An application in the competitiveness of SMEs across different EU beneficiary regions
2021, Omega (United Kingdom)
Citation Excerpt :
The Value-Based DEA model suggested in Gouveia et al. [32] also overcomes the problem of the scales, since all the inputs and outputs are converted into values. The Value-Based DEA is different from the weighted additive model [1] since it enables incorporating value judgments, using concepts from multiattribute utility theory (MAUT). According to the Value-Based DEA, the DMUs are viewed as alternatives of a multiple criteria decision analysis (MCDA) model, where the criteria are the input/output factors, considering that “the inputs are usually the “less-the-better” type of performance measures and the outputs are usually the “more-the-better” type of performance measures” [19], whereas their transformation process is not important.
The funds dedicated to the cohesion policy are aimed at attaining the convergence of wealth levels across the European Union (EU) member states. These constitute the second-highest group of expenditures in the EU budget and thus their evaluation assumes a prominent role. Their assessment can be carried out through different tools and methodologies, all of them with their own merits and flaws. For instance, macroeconomic models allow assessing the potential impact of EU funds on economic growth, but disregard management issues. Other modelling approaches consider direct econometric estimations which might bring biased estimates of the impacts of Structural Funds if some variables are omitted. A different possible tool is Data Envelopment Analysis (DEA), which is a non-parametric method to measure the relative efficiency of Decision-Making Units (DMUs), allowing for the consideration of multiple inputs and outputs in global performance evaluation. In this work we employ the Value-Based DEA approach, which combines DEA with Multiple Criteria Decision Aiding (MCDA) and enables performing a robustness analysis of the results in face of uncertain information, considering the main factors that might influence the efficiency of the implementation of Structural Funds. Specifically, we address the assessment of its application in the competitiveness of small and medium-sized enterprises (SMEs), in different beneficiary regions of the EU. Our analysis helped in the identification of best practices, sources of inefficiency and gaps regarding the benchmark regions/countries, thus leading to shape opportunities for improvement. Overall, we were able to ascertain that national inefficient programmes mainly need to reduce their dependence on EU co-funding to become efficient, whereas almost all inefficient regional programmes need to improve their capacity of execution. Nevertheless, differences were found on the factors that require adjustments when considering regions’ categories.
Benchmarking of maintenance and outage repair in an electricity distribution company using the value-based DEA method
2015, Omega (United Kingdom)
Citation Excerpt :
The present study combines DEA with multiple criteria decision analysis (MCDA) including relevant preferential information elicited from the DM using value-based DEA [26,27]. This method is based on the additive DEA model with oriented projections [28], making use of concepts developed in the field of MCDA under imprecise information [29,30]. The present paper presents a benchmarking study for one of the activities performed by EDP Distribuição (EDP-D)—maintenance and outage repair.
Benchmarking of electricity distribution utilities has been widely used as a means to contribute for the adoption or reinforcement of enhanced competitiveness and innovation practices to optimize costs, increase customer satisfaction, improve corporate image and maximize profits. The purpose of this paper is to present a benchmarking study for the maintenance and outage repair activity carried out by a Portuguese electricity distribution company, EDP Distribuição (EDP-D), using the value-based DEA method, which builds on links between data envelopment analysis (DEA) and multiple criteria decision analysis (MCDA). This study illustrates the impact of the incorporation of managerial preferences in the classification and ranking of 40 network areas served by EDP-D, confronting the results with a previous study based on a BCC DEA model. In order to deal with the underlying uncertainty, the value-based DEA method for performance evaluation is adapted to include the concept of super-efficiency. Besides identifying best practices, sources of inefficiency, gaps relatively to best practices and opportunities for improvement, this analysis supports the introduction of corrective measures and informs decisions about future goals.
Are green and socially responsible funds more efficient than conventional funds? A DEA approaches
2024, Journal of Economic Studies

View all citing articles on Scopus

View full text

Components of efficiency evaluation in data envelopment analysis

Abstract

Socio-Economic Planning Sciences

European Journal of Operational Research

European Journal of Operational Research

Journal of Econometrics

Journal of Econometrics

Journal of Econometrics

Using data envelopment analysis to measure the efficiency of not-for-profit organizations: A critical evaluation — Comment

Managerial and Decision Economics