Power Of Data Envelopment Analysis Research Articles

CI-DEA: A Way to Improve the Discriminatory Power of DEA—Using the Example of the Efficiency Assessment of the Digitalization in the Life of the Generation 50+

Data envelopment analysis (DEA) is a popular and universal method for examining the efficiency with which decision-making units (DMUs) transform multiple inputs into multiple outputs. However, DEA has its limitations, one of them being its decreasing discriminatory power when the number of analyzed DMUs is insufficient or when there are too many variables (inputs/outputs) describing them. When resigning from any of the variables is impossible or undesired, or when the number of units cannot be increased, CI-DEA, a method proposed in this article, proves to be helpful. It consists of replacing the inputs and/or outputs of the studied DMUs with a smaller number of composite indicators. The aggregation of variables is not based on subjective decisions of the analyst, but depends solely on correlations that exist among variables. The construction of the CI-DEA model makes the interpretation of the results unambiguous and easy. The reliability of the results obtained with CI-DEA have been confirmed by extensive simulation studies performed under conditions of predetermined real-efficiency of DMUs. The usefulness of CI-DEA on real data has been demonstrated on the example of the efficiency assessment of the digitalization in the life of the Generation 50+ in 32 European countries.

A modified super-efficiency network data envelopment analysis: Assessing regional sustainability performance in China

The super-efficiency technique aims to improve the discriminating power of data envelopment analysis (DEA) through re-evaluation after excluding the evaluated object from the reference set. However, the super-efficiency radial network DEA with undesirable production variables faces the infeasibility problem as the traditional DEA. To solve this issue, this paper detects one new origin of infeasibility in network DEA not existing in traditional DEA and provides the necessary and sufficient conditions of infeasibility occurrence. Then, a modified super-efficiency radial network DEA is developed without infeasibility. We apply the modified model to assess the regional sustainability performance in China from 2009 to 2017. Considering the internal connectivity and influences among the economic, environmental, and social dimensions of sustainability, we construct a three-stage network system, i.e., economic growth (EG), waste disposal (WD), and health protection (HP) subsystems. The results show that the regional sustainability performance of China was on a downward trend until 2015 but has improved significantly since then. Besides, the status quo of a regional disparity in sustainability performance is confirmed. The results suggest that the eastern region remains the leader in promoting the regional sustainability of China, the central and western regions are trying to catch up with it, and the northeast region still needs more support from the government to keep pace with the coordinated development of China.

The curse of dimensionality of decision-making units: A simple approach to increase the discriminatory power of data envelopment analysis

Data envelopment analysis (DEA) is a technique for identifying the best practices of a given set of decision-making units (DMUs) whose performance is categorized by multiple performance metrics that are classified as inputs and outputs. Although DEA is regarded as non-parametric, the sample size can be an issue of great importance in determining the efficiency scores for the evaluated units, empirically, when the use of too many inputs and outputs may result in a significant number of DMUs being rated as efficient. In the DEA literature, empirical rules have been established to avoid too many DMUs being rated as efficient. These empirical thresholds relate the number of variables with the number of observations. When the number of DMUs is below the empirical threshold levels, the discriminatory power among the DMUs may weaken, which leads to the data set not being suitable to apply traditional DEA models. In the literature, the lack of discrimination is often referred to as the “curse of dimensionality”. To overcome this drawback, we provide a simple approach to increase the discriminatory power between efficient and inefficient DMUs using the well-known pure DEA model, which considers either inputs only or outputs only. Three real cases, namely printed circuit boards, Greek banks, and quality of life in Fortune’s best cities, have been discussed to illustrate the proposed approach.

Measuring the Performance Efficiency of Hospitals: PCA – DEA Combined Model Approach

Objectives: The Government provides primary health care services to the poor and needy people through District Hospitals. Primary care is an ongoing care being focused on person over time that fulfils the health related requirements of people. This necessitates studying the efficient functioning of public hospitals. So the author concentrated and considered to analyse the performance of District Hospitals in the state of Tamil Nadu. Methods/Statistical Analysis: To attain the above objective one of the nonparametric methods namely Data Envelopment Analysis (DEA) has applied. It is a mathematical technique based on linear programming problem and it measures the relative efficiency of similar type of organizations termed as Decision Making Units (DMUs). In this study each DMU refers to the District Hospital in the state of Tamil Nadu. In DEA, normally there exists a significant correlation between the inputs and outputs. Inclusion of more number of inputs and /or outputs in DEA results in getting a more number of efficient units. Therefore, select the appropriate inputs and outputs based on the experts’ advice who know their characteristics very well. A clear understanding of the characteristics of input/output variables will nullify the above deficiency and will really results with exact number of efficient units. An attempt is made to rectify the deficiency in introducing the technique viz., Principal Component Analysis. Principal Component Analysis helps the decision maker to reduce the data structure into certain principal components which are essential for identifying efficient DMUs. It is important to note that we have used the basic BCC model for the entire analysis. Findings: The author has considered 31 DMUs for the study using BCC model. The data results with 13 DMUs out of 31 DMUs as efficient. Subsequently with the same original data 3 PCs on input and output explains 98 percent of the total variance and this has resulted with only 3 DMUs as efficient. Then we have considered 2PCs on input and output. This has resulted with 90.31 percent variance in the case of input and 95.78 percent variance in the case of output. Normally in Principal Component analysis, if the variance lies between 80 percent to-90 percent it is judged as a meaningful one. The above computations result with 2 DMUs efficient. Finally, we have attempted to identify the efficient units with the above expected variance interval 80 percent to 90 percent. This has resulted with 90 percent variance explained with 2 input variable and one output variable with 89 percent explained variance. This also resulted with only 2 efficient DMUs. It is concluded that Principal Component Analysis plays an important role in the reduction of input output variables and helps in identifying the efficient DMUs and improves the discriminating power of DEA. Application/Improvements: Introduction of PCA with DEA is definitely is an improvement which helps the decision maker to apply in wider sense and to take proper managerial decision.

Efficiency Evaluation of State Transport Undertakings of India using DEA-NN approach

The economy of any nation depends on the structure and functioning of its various sectors. Transport sector is one of the vital sectors for the financial system of any developing country. All other sectors are dependent on it either directly or indirectly. Thus improving the efficiency of this sector has become a major concern for the operators and the policy makers. The present paper presents an amalgamation of the two non-parametric techniques, Data Envelopment Analysis (DEA) and Neural Networks (NNs) to compute the efficiency scores of State Transport Undertakings of India. DEA is used to compute the efficiency scores of 27 DMUs. These scores are used to train a neural network model, namely the BPN model. The algorithm is developed and used for predicting the efficiency scores of other units of the data set. The results obtained are comparable and it has been shown that this approach helps in improving the discriminatory power of DEA.

Increasing the discrimination power of data envelopment analysis

In data envelopment analysis (DEA), to discriminate between efficient units, several ranking methods have been proposed by different authors from various points of views. However, despite of the fact that each technique has some advantages and disadvantages, all of them will face the relatively high computational complexity level. Moreover, different ranking procedures yield to different results. Although there are many ranking approaches in DEA literature, there is a need to provide a complete ranking on efficient units with a lower complexity. The current paper proposes a complete ranking method for fully ranking of all DMUs. Furthermore, this approach makes use of a common set of weights for all DMUs. In the proposed ranking approach, the infeasibility and instability problems of the existing methods have been removed. Moreover, the computational effort of the approach is relatively low in comparison to the existing methods. Sample and real cases will be presented for more illustration.

Some remarks on the two-level DEA model

The two-level DEA model was introduced to increase the discriminational power of Data Envelopment Analysis (DEA) models. This nonlinear model was presented by Meng et al. (2008) [3], and then converted into a linear model by Kao (2008) [4]. In this paper two subjects will be discussed: first, we show that the two-level DEA model is a special case of DEA models where weight restrictions are applied. Then, we express that the nonlinear model is equivalent to the conventional DEA model.

Ranking efficient decision-making units in data envelopment analysis using fuzzy concept

This paper introduces a new mathematical method for improving the discrimination power of data envelopment analysis and to completely rank the efficient decision-making units (DMUs). Fuzzy concept is utilised. For this purpose, first all DMUs are evaluated with the CCR model. Thereafter, the resulted weights for each output are considered as fuzzy sets and are then converted to fuzzy numbers. The introduced model is a multi-objective linear model, endpoints of which are the highest and lowest of the weighted values. An added advantage of the model is its ability to handle the infeasibility situation sometimes faced by previously introduced models.

Two-level DEA approaches in research evaluation

It is well known that the discrimination power of data envelopment analysis (DEA) models will be much weakened if too many input or output indicators are used. It is a dilemma if decision makers wish to select comprehensive indicators, which often have some hierarchical structures, to present a relatively holistic evaluation using DEA. In this paper we show that it is possible to develop DEA models that utilize hierarchical structures of input–output data so that they are able to handle quite large numbers of inputs and outputs. We present two approaches in a pilot evaluation of 15 institutes for basic research in the Chinese Academy of Sciences using the DEA models.

A Cross-Efficiency Profiling For Increasing Discrimination in Data Envelopment Analysis

Data Envelopment Analysis (DEA) cannot provide adequate discrimination among effieient decision making units (DMUs). To discriminate these effieient DMUs is an interesting research subject. The purpose of this paper is to present a Cross-Efficiency Prollling (CEP) model which can be used to improve discriminalitin power of DEA and condiicl a methodological comparison of CEP anti the other developed methods without a priori information. CEP retains ihe original spirilot DEA in trying to extract as much information as ptissible from the data without requiring pre-selecied weights on inputs and outputs. We propose ihat inputs which are not substitutes for each other be assessed separately and only with respect to outputs which consume them or to which they are otherwise related. In this way input-specific ratings based on the concept of cross-efficiency measure arc derived giving a profile for each DMU. We will demonstrate that CEP is more discriminating through an example taken from Baker and Talluri [Computer and Industrial Engineering, 32(1), 101–108 (1997)].

Improving the discriminating power of DEA: focus on globally efficient units

We introduce in this paper the global efficiency approach as a means to improve the discriminating power of Data Envelopment Analysis (DEA). To discriminate further among the DEA efficient units, we deal only with the units that can maintain their efficiency score under common weighting structures. Then we proceed further to ranking the whole set of DEA efficient units. We compare the global efficiency approach with the multi-criteria DEA and the cross-efficiency approaches on the basis of characteristic numerical examples drawn from the literature.

Improving the discriminating power of DEA: focus on globally efficient units

We introduce in this paper the global efficiency approach as a means to improve the discriminating power of Data Envelopment Analysis (DEA). To discriminate further among the DEA efficient units, we deal only with the units that can maintain their efficiency score under common weighting structures. Then we proceed further to ranking the whole set of DEA efficient units. We compare the global efficiency approach with the multi-criteria DEA and the cross-efficiency approaches on the basis of characteristic numerical examples drawn from the literature.

A decision model for evaluation of flexible manufacturing systems in the presence of both cardinal and ordinal factors

This paper presents a model for evaluating alternative Flexible Manufacturing Systems by considering both quantitative and qualitative factors. The evaluation process utilizes a recently proposed Data Envelopment Analysis (DEA) model, which incorporates both ordinal and cardinal measures, in conjunction with new extensions in DEA. The paper contributes to the body of knowledge in two important ways. First, it provides a new model based on pair-wise comparisons of specific alternatives, which significantly improves the discriminatory power of DEA. The second major contribution is to detail the model's utility in its application for evaluating strategic manufacturing technologies, specifically Flexible Manufacturing Systems. The consideration of both tangible and intangible factors, which is a primary goal in strategic evaluation of systems, is achieved in this methodology. The model is illustrated through an application on a previously reported data set. The analysis of results provide useful insights that include both seller's and buyer's perspectives of system evaluation.