Data envelopment analysis

2005

Section 3.9 in Chapter 3 introduced the topic of non-discretionary variables and appUed it to examples drawn from a study of Texas schools. In that study it was necessary to allow for variations in "minority," "economically disadvantaged" and "low English proficiency" students who had to be dealt with in different schools. These input variables were "non-discretionary." That is, they could not be varied at the discretion of individual school managers but nevertheless needed to be taken into account in arriving at relative efficiency evaluations. The approach taken in Chapter 3, as adapted from Banker and Morey ^ (1986), took form in the following model: mi n 0-si'^s-+Y,st]

2007

Handbook of Research on Strategic Performance Management and Measurement Using Data Envelopment Analysis

This chapter provides the theoretical foundation and background on Data Envelopment Analysis (DEA) method and some variants of basic DEA models and applications to various sectors. Some illustrative examples, helpful resources on DEA, including DEA software package, are also presented in this chapter. DEA is useful for measuring relative efficiency for variety of institutions and has its own merits and limitations. This chapter concludes that DEA results should be interpreted with much caution to avoid giving wrong signals and providing inappropriate recommendations.

Computers & Industrial Engineering, 2017

In recent years, several mixed integer linear programming (MILP) models have been proposed for determining the most efficient decision making unit (DMU) in data envelopment analysis. However, most of these models do not determine the most efficient DMU directly; instead, they make use of other less related objectives. This paper introduces a new MILP model that has an objective similar to that of the super-efficiency model. Unlike previous models, the new model's objective is to directly discover the most efficient DMU. Similar to the super-efficiency model, the aim is to choose the most efficient DMU. However, unlike the super-efficiency model, which requires the solution of a linear programming problem for each DMU, the new model requires that only a single MILP problem be solved. Consequently, additional terms in the objective function and more constraints can be easily added to the new model. For example, decision makers can more easily incorporate a secondary objective such as adherence to a publicly stated preference or add assurance region constraints when determining the most efficient DMU. Furthermore, the proposed model is more accurate than two recently proposed models, as shown in two computational examples.

2012

2014

Data Envelopment Analysis (DEA) which is applied to evaluate the relative efficiency of decision making units (DMU), is a mathematical programming approach. The efficiency in the classical DEA is "the ratio of the sum of the weighted outputs to the sum of weighted inputs". In order to obtain the maximum efficiency score for each DMU under evaluation, different weights are assigned to the inputs and outputs of the DMU. Classical DEA models allow weight flexibility. Thus, zero weights can be assigned to some important inputs and outputs of the DMU. In this case, such inputs and outputs will be ignored in the evaluation and will be found unrealistic results. Weight restrictions are utilized to eliminate the problem. Input and output variables in the production process are associated with the degree of correlations between these variables. Previous papers didn't consider the relationship between inputs and outputs. In this study, the weights are defined by correlations between input and output variables. So, the new DEA models constrained with correlation coefficients (CCRCOR and BCCCOR) are developed. The CCRCOR and BCCCOR models and other known DEA models were applied on some datasets in the literature. The results were compared with the Spearman rank test. According to the results, the CCRCOR and BCCCOR models provided a more balanced weight distribution than the other models.

Computers & Industrial Engineering, 2015

In recent years, several mixed integer linear programming (MILP) models have been proposed for determining the most efficient decision making unit (DMU) in data envelopment analysis. However, most of these models do not determine the most efficient DMU directly; instead, they make use of other less related objectives. This paper introduces a new MILP model that has an objective similar to that of the super-efficiency model. Unlike previous models, the new model's objective is to directly discover the most efficient DMU. Similar to the super-efficiency model, the aim is to choose the most efficient DMU. However, unlike the super-efficiency model, which requires the solution of a linear programming problem for each DMU, the new model requires that only a single MILP problem be solved. Consequently, additional terms in the objective function and more constraints can be easily added to the new model. For example, decision makers can more easily incorporate a secondary objective such as adherence to a publicly stated preference or add assurance region constraints when determining the most efficient DMU. Furthermore, the proposed model is more accurate than two recently proposed models, as shown in two computational examples.

An Introduction to Efficiency and Productivity Analysis, 1998

This chapter continues the discussion of data envelopment analysis (DEA) which began in the previous chapter. In the previous chapter, we introduced the efficiency measurement concepts of Farrell (1957) and described how they could be implemented using the linear programming approach known as DEA. We discussed the basic constant returns to scale (CRS) and variable returns to scale (VRS) DEA models from both the input-and output-orientations. In this chapter we discuss some popular extensions of these basic DEA models. The extensions we consider involve allocative efficiency, environmental variables, non-discretionary variables, the treatment of slacks and congestion efficiency. We also provide an empirical example using data on Australian universities. 7.2 Price Information and Allocative Efficiency If price information is available and a behavioural objective, such as cost minimisation or revenue or profit maximisation, is appropriate, then it is possible to measure allocative efficiencies as well as technical efficiencies. To achieve this, two sets of linear programs are required; one to measure technical efficiency and the other to measure economic efficiency. The allocative efficiency measure is then obtained residually as described in the previous chapter. We now illustrate this procedure using the cost minimisation case. T. Coelli et al.

Journal of Mathematical and Computational Science, 2021

Data envelopment analysis (DEA) is one of the widely accepted optimization technique uses to measure the relative efficiency of organizational units where multiple inputs and outputs are present. The significance of DEA results depends on the variables selected for DEA modelling. One of the main challenges in data envelopment analysis modelling is of identify the significant input and output variables for DEA modelling. In this study, we propose an enhanced stepwise method to identify the significant and insignificant input and output variable by reducing the iterations process in stepwise method. The statistical significance of the input and output variables evaluated using the statistical methods: Least significance difference (LSD), and Welch's statistics. The proposed method applied to the Indian banking sector and the results have shown that the proposed model significantly identified the significant and 704 SUBRAMANYAM, DONTHI, KUMAR, AMALANATHAN, ZALKI insignificant input and output variables with least loss of information.