Reliability and Statistical Computing pp 289-304 | Cite as
Data Envelopment Analysis as a Tool to Evaluate Marketing Policy Reliability
- 221 Downloads
Abstract
In this paper we describe the Data Envelopment Analysis (DEA) research design and its applications for effectiveness evaluation of company marketing strategies. We argue that DEA is an efficient instrument for use in academia and industry to compare a company’s business performance with its competitors’. This comparison provides the company with information on the closest competitors, including evaluating strategies with similar costs, but more efficient outcomes (sales). Furthermore, DEA provides suggestions on the optimal marketing mix to achieve superior performance.
Keywords
Data envelopment analysis Optimization Business performance Program evaluation1 Introduction
Certain limits are imposed on the optimization algorithm. In basic DEA models, the value of the results cannot exceed the value of the expended resources. However, this assumption has been relaxed in more advanced models, called super-efficiency models (see, e.g., [16, 21]). A unit is 100% efficient if none of its inputs or outputs can be further improved without worsening other inputs or outputs. Adding new units into the mix may change the outcome of the estimation for any of the remaining units.
The optimal value of β_{k} becomes the efficiency of the DMU k. By virtue of dual theorem of linear programming (LP), z = β*. This is derived from the foundational property of linear programming, where a dual of a LP is created from the original program. It is done in the following way: each variable in the primal LP is a constraint in a dual LP; each constraint in the primal LP is a variable in the dual LP; the objective direction is reversed—maximum in the primal is the minimum in the dual and vice versa [17]. Therefore, in DEA, either of the problems can be used, depending on the need, to evaluate efficiency as the ability to maximize outcomes or minimize inputs. As a result of the optimization procedure, we have a matrix of the optimum values of {x_{km}; y_{kn}}, and due to the imposed constraints, the resulting efficiency of each DMU cannot be greater than 1.
2 DEA Research Design
Variable selection and choice of return to scale are crucial for DEA research design. Both should be either theoretically driven or depend on an applied request from the client.
2.1 Variable Selection
In standard DEA, it is assumed that a variable constitutes either an input or an output. However, just as with regression methods, where selection of a dependent variable depends on a research context, in DEA some measures can play either input or output roles. When theoretical roles of variables are not clear, a mathematical approach to variable selection may be necessary. Zhu and Cook [22] developed models that can help classify variables as either input or output; Cook et al. [8] provide the methodology for evaluating performance of the units where some factors can simultaneously play both the input and the output roles.
In addition, in real life, variables used for analysis are rarely homogeneous. For example, in the context of marketing research, such variables as internal company resources (choice of marketing mix, tangible and intangible resources) are discretionary for each company (meaning, the company has the ability to control their production and use), whereas the global competitive environment in which the company operates is non-discretionary. DEA allows for such heterogeneity in the data, providing an option for the researcher to select the non-discretionary indices that the DMU cannot control and appropriately exclude them from the calculation of an individual unit’s efficiency, while allowing them to remain in the model for calculating the efficient frontier. Detailed description of models with non-discretionary inputs is provided, e.g., in Muñiz [18], Bessent et al. [4], and Banker and Morey [3].
2.2 Choice of Return to Scale
The economic concept of returns to scale (RTS) has further extended the applicability of DEA models [9]. Original extensions were suggested by Banker [1] and Banker et al. [2]. Nicholson [19] provides an intuitive explanation of constant returns to scale (CRS) as an “increase in outputs proportionate to the increase in inputs;” less than proportionate increase means diminishing returns, and more than proportional—increasing returns to scale (IRS). Most DEA software tools now provide options that incorporate all types of returns to scale for estimating the efficiency of the units; VRS models allow for units’ returns to vary between the DMUs. Non-increasing returns to scale (NIRS) put an additional limitation on the VRS, where returns to scale for individual units are limited to constant or decreasing, forming a concave production function. While it is possible to determine the return to scale mathematically, there should be a theoretical foundation behind the model that determines that type of returns that one expects the DMUs to follow.
3 DEA-Generated Results
Depending on the program used, in addition to evaluation of efficiency, the output includes weights of each index in the efficiency calculations, slacks, improvements, graphical outputs, a subset of peer DMUs for each inefficient unit, and some others. Theoretical description of the most common outputs follows.
3.1 Efficiency
Efficiency is the relative performance indicator of a DMU in a group that it is being compared against. It is measured on a scale from 0 to 1, or as a percentage, depending on the software. Efficiency of one (100%) means that the unit is relatively efficient; anything less indicates that it is inefficient, with the actual value indicating the level of efficiency. Inefficiency means that either the inputs are not fully utilized, given the outcome, and could potentially generate a greater outcome (input-based models), or the outcome needs to be augmented (output-based models).
3.2 Weights
In the original model, Charnes et al. [7] accounts for the fact that DMUs may value inputs and outputs differently, so each unit is given the “freedom,” mathematically, to vary the set of weights that allow it to achieve the maximum possible efficiency position relative to other units. The weights, therefore, are very flexible and unit-free, and are unrelated to any other input or output. If a unit is inefficient even with the most favorable choice of weights, relative to other units, then it is a strong statement to the unit’s true lack of efficiency.
3.3 Slacks
Reducing inputs or augmenting outcomes alone may not always be sufficient. This situation is defined as a “slack,” meaning excessive inputs or missing outputs. This result shows which resources are utilized completely to achieve a certain outcome, and which have an excess and could be reduced to improve performance.
3.4 Improvements (Targets)
One of the main benefits of DEA is estimating the magnitude of changes in the resource that is required for the unit to achieve the 100% efficiency. Improvements are provided in the form of changes to variables on the original scale. Some software packages may offer an option of a percentage change.
3.5 Peer Group (Peers, Reference Sets)
For every unit that is inefficient, DEA finds at least one unit that is efficient with the same basic pattern of inputs and outputs. Direct comparison of the peers is not always possible without additional data scaling, which can be done on either inputs or outputs. However, the peer group allows evaluating each inefficient unit’s unique path to efficiency.
3.6 Cross-Efficiency
In addition to building frontiers to identify the most efficient cases, DEA constructed the cross-efficiency matrix—a table where the number of rows (i) and columns (j) equals the number of units in the analysis. For each cell (ij), the efficiency of unit ij is computed with weights that are optimal to unit j. The higher the values in a given column j, the more likely it is that the unit ij is an example of more efficiently operating practices. Doing so DEA allows us to match all units depending on the similarity of their efficiency function.
4 Evaluating Efficiency Over Time
DEA works with panel data. Because quite often scientists and practitioners are interested in the development of a phenomenon over time [13], this option can become invaluable for longitudinal efficiency comparison.
In classical productivity literature, changes in efficiency over time can be broadly divided into five categories [12]: (1) producing the same outputs with fewer resources, (2) producing more outputs without changing the resources used, (3) producing more outputs with fewer resources, (4) provide a larger increase in the outputs for an increase in inputs, and (5) provide a smaller reduction in outputs for the expected decrease in resources. The first three components are referred to as “technical efficiency,” and the last two—as “scale efficiency.” The total productivity growth achieved by the unit is estimated through the Malmquist index, first introduced by Caves et al. [5] and later extended by Fare et al. [11]. It is defined using the distance functions and does not require any assumptions regarding efficiency; therefore, it can distinguish between the factors causing chances in productivity. In a DEA setting, Malmquist index measures the change between data points by providing the ratio of distances from each data point to a common technology. As a result, it is decomposed into the technological change (TC) and efficiency change (EC). The latter is in turn is divided into the PEC (pure efficiency change) and SEC (scale efficiency change) indices for variable and constant returns to scale [20], respectively. Technical efficiency is the overall change in production technology, which reflects the movement in the production frontier. Pure efficiency change component is measured relative to the true VRS frontier; where SEC is the “magnitude” component [11], which quantifies the productivity loss or gain of the unit itself. As a result, the Malmquist index is the product of change in relative efficiency between two different time periods, and the value of index equal to 1 implies no change in total factor productivity, less than 1—deterioration, more than 1—growth. Same interpretation applies to each individual component, and the different DMUs can be compared to each other directly in their changes of the Total Factor Productivity Change (TFPC).
5 An Application: Effectiveness of the Marketing Strategies
Marketing efficiency scores, %
Name | 2017 | 2018 |
---|---|---|
car 1 | 100 | 100 |
car 2 | 100 | 100 |
car 4 | 100 | 100 |
car 5 | 100 | 100 |
car 9 | 69.05 | 100 |
car 11 | 100 | 100 |
car 13 | 100 | 100 |
car 14 | 100 | 100 |
car 15 | 100 | 100 |
car 3 | 100 | 83.58 |
car 12 | 100 | 76.13 |
car 6 | 81.3 | 70.6 |
car 7 | 77.9 | 69 |
car 17 | 56.98 | 57.63 |
car 8 | 85.78 | 57.19 |
car 10 | 68.25 | 53.29 |
car 16 | 11.79 | 21.69 |
Marketing weights, 2018
Name | Digital | Outdoor | Press | Radio | Sat TV | TV Nat | TV Reg |
---|---|---|---|---|---|---|---|
car 1 | 0 | 0 | 0 | 0 | 0 | 0 | 1 |
car 2 | 0 | 0 | 0 | 0 | 1 | 0 | 1 |
car 3 | 0 | 1 | 0 | 0 | 0 | 0 | 0 |
car 4 | 0 | 0 | 1 | 0 | 0 | 0 | 1 |
car 5 | 0 | 1 | 0 | 0 | 0 | 0 | 1 |
car 6 | 0 | 1 | 0 | 0 | 0 | 0 | 1 |
car 7 | 0 | 1 | 0 | 1 | 0 | 0 | 1 |
car 8 | 0 | 0 | 1 | 0 | 1 | 0 | 1 |
car 9 | 0 | 1 | 0 | 0 | 0 | 0 | 1 |
car 10 | 0 | 0 | 0 | 0 | 1 | 1 | 1 |
car 11 | 0 | 1 | 0 | 0 | 1 | 0 | 1 |
car 12 | 0 | 0 | 0 | 0 | 1 | 1 | 1 |
car 13 | 1 | 1 | 0 | 0 | 1 | 0 | 1 |
car 14 | 0 | 0 | 1 | 0 | 1 | 1 | 1 |
car 15 | 0 | 1 | 0 | 0 | 1 | 1 | 1 |
car 16 | 1 | 1 | 0 | 0 | 1 | 0 | 1 |
car 17 | 0 | 1 | 0 | 0 | 0 | 0 | 1 |
Total | 2 | 10 | 3 | 1 | 9 | 4 | 16 |
Marketing slacks, 2018
Name | Digital | Outdoor | Press | Radio | Sat TV | TV Nat | TV Reg |
---|---|---|---|---|---|---|---|
car 1 | 0 | 1 | 0 | 0 | 0 | 0 | 1 |
car 2 | 0 | 0 | 0 | 0 | 0 | 1 | 0 |
car 3 | 1 | 0 | 1 | 1 | 1 | 1 | 1 |
car 4 | 1 | 1 | 0 | 1 | 0 | 1 | 0 |
car 5 | 1 | 0 | 0 | 1 | 0 | 1 | 0 |
car 6 | 0 | 0 | 1 | 1 | 1 | 1 | 0 |
car 7 | 1 | 0 | 1 | 0 | 1 | 1 | 0 |
car 8 | 1 | 1 | 0 | 1 | 0 | 1 | 0 |
car 9 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
car 10 | 1 | 1 | 0 | 1 | 0 | 0 | 0 |
car 11 | 1 | 0 | 0 | 1 | 0 | 1 | 0 |
car 12 | 1 | 0 | 1 | 1 | 0 | 0 | 0 |
car 13 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
car 14 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
car 15 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
car 16 | 0 | 0 | 1 | 1 | 0 | 1 | 0 |
car 17 | 1 | 0 | 1 | 0 | 1 | 1 | 0 |
Total | 9 | 4 | 6 | 9 | 4 | 10 | 2 |
In Table 3, the one against a channel for a specific model indicates that the company spent too much in resources for the level it achieved for a certain brand. When taken together, this information can help the company evaluate its marketing strategy. For example, spending on advertising in national TV was efficient for Cars 1, 9, 10, 12, 13–15; for all the other ten models, the company can cut national TV advertising without hurting the sales. DEA provides the exact “slack” numbers that could be cut without losing efficiency.
Marketing improvements (targets), 2018, %
Name | Digital | Outdoor | Press | Radio | Sat TV | TV Nat | TV Reg | Sales |
---|---|---|---|---|---|---|---|---|
car 1 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
car 2 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
car 3 | −18.76 | 0 | −72.39 | −19.03 | −98.77 | −39.99 | −18.33 | 19.64 |
car 4 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
car 5 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
car 6 | 0 | 0 | −43.31 | −15.97 | −76.12 | −27.71 | 0 | 41.64 |
car 7 | −39.11 | 0 | −2.37 | 0 | −71.57 | −11.59 | 0 | 44.92 |
car 8 | −86.88 | −34.41 | 0 | −86 | 0 | −15.96 | 0 | 74.84 |
car 9 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
car 10 | −63.82 | −73.88 | 0 | −58.95 | 0 | 0 | 0 | 87.64 |
car 11 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
car 12 | −23.67 | 0 | −22.25 | −57.56 | 0 | 0 | 0 | 31.36 |
car 13 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
car 14 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
car 15 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
car 16 | 0 | 0 | −78.14 | −2.6 | 0 | −63.91 | 0 | 361.09 |
car 17 | −31.25 | 0 | −66.7 | 0 | −48.59 | −23.94 | 0 | 73.52 |
Marketing peers (lambdas), 2018
Name | car 1 | car 2 | car 4 | car 5 | car 9 | car 11 | car 13 | car 14 | car 15 |
---|---|---|---|---|---|---|---|---|---|
car 1 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
car 2 | 0.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
car 3 | 0.59 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.41 |
car 4 | 0.00 | 0.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
car 5 | 0.00 | 0.00 | 0.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
car 6 | 0.10 | 0.18 | 0.00 | 0.34 | 0.00 | 0.00 | 0.00 | 0.00 | 0.38 |
car 7 | 0.06 | 0.16 | 0.00 | 0.56 | 0.00 | 0.00 | 0.00 | 0.00 | 0.22 |
car 8 | 0.17 | 0.00 | 0.00 | 0.03 | 0.00 | 0.00 | 0.00 | 0.23 | 0.56 |
car 9 | 0.00 | 0.00 | 0.00 | 0.00 | 1.00 | 0.00 | 0.00 | 0.00 | 0.00 |
car 10 | 0.07 | 0.12 | 0.00 | 0.00 | 0.04 | 0.00 | 0.00 | 0.26 | 0.51 |
car 11 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1.00 | 0.00 | 0.00 | 0.00 |
car 12 | 0.00 | 0.03 | 0.00 | 0.00 | 0.18 | 0.12 | 0.38 | 0.30 | 0.00 |
car 13 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1.00 | 0.00 | 0.00 |
car 14 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1.00 | 0.00 |
car 15 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 1.00 |
car 16 | 0.00 | 0.00 | 0.00 | 0.00 | 0.04 | 0.07 | 0.03 | 0.00 | 0.87 |
car 17 | 0.17 | 0.46 | 0.00 | 0.18 | 0.00 | 0.00 | 0.00 | 0.00 | 0.20 |
Figure 1 shows a directed network, where the inefficient models are connected to the efficient—those which, with similar costs, achieved a greater sales result. Several things can be learned from this graph. First, connected car models are competitors to the efficient models; in other words, they use the same marketing strategy, but less efficiently. Second, because they follow the same marketing strategy, they are also competitors to each other—or, to similar inefficient models. Finally, this network can also be interpreted and analyzed as pseudo-bimodal, with one mode of “efficient” units, and another—of inefficient. Standard bimodal network analysis can then apply.
Marketing cross efficiency, 2018
Name | car 1 | car 2 | car 3 | car 4 | car 5 | car 6 | car 7 | car 8 | car 9 | car 10 | car 11 | car 12 | car 13 | car 14 | car 15 | car 16 | car 17 |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
car 1 | 100.0 | 100.0 | 56.3 | 78.7 | 74.5 | 48.6 | 52.2 | 51.3 | 100.0 | 52.7 | 46.2 | 53.4 | 44.0 | 100.0 | 100.0 | 4.8 | 43.8 |
car 2 | 100.0 | 100.0 | 41.2 | 64.5 | 100.0 | 40.5 | 44.6 | 56.2 | 15.8 | 48.9 | 63.2 | 26.3 | 35.8 | 100.0 | 100.0 | 15.2 | 42.3 |
car 3 | 99.9 | 20.4 | 83.6 | 11.3 | 55.2 | 26.9 | 26.5 | 29.3 | 17.6 | 4.5 | 26.7 | 6.4 | 2.5 | 10.8 | 95.0 | 10.1 | 17.6 |
car 4 | 100.0 | 100.0 | 50.3 | 100.0 | 100.0 | 52.4 | 61.3 | 38.1 | 54.5 | 37.4 | 56.1 | 23.9 | 30.7 | 11.5 | 39.8 | 3.0 | 34.9 |
car 5 | 100.0 | 100.0 | 62.3 | 65.9 | 100.0 | 59.6 | 63.8 | 51.7 | 100.0 | 31.3 | 69.2 | 44.4 | 21.9 | 79.6 | 100.0 | 12.9 | 51.0 |
car 6 | 99.8 | 99.7 | 69.6 | 61.6 | 99.3 | 70.6 | 56.5 | 27.1 | 87.2 | 21.9 | 69.9 | 32.5 | 17.7 | 37.8 | 90.6 | 27.0 | 52.6 |
car 7 | 99.9 | 99.8 | 69.9 | 56.2 | 99.7 | 67.8 | 69.0 | 28.3 | 60.8 | 20.8 | 76.5 | 18.3 | 11.7 | 31.5 | 94.3 | 20.1 | 57.7 |
car 8 | 98.9 | 54.6 | 20.3 | 28.8 | 96.3 | 18.9 | 20.9 | 57.2 | 4.3 | 29.2 | 43.2 | 9.2 | 15.0 | 76.4 | 71.8 | 11.7 | 24.0 |
car 9 | 100.0 | 100.0 | 62.3 | 65.9 | 100.0 | 59.6 | 63.8 | 51.7 | 100.0 | 31.3 | 69.2 | 44.4 | 21.9 | 79.6 | 100.0 | 12.9 | 51.0 |
car 10 | 100.1 | 100.2 | 56.4 | 78.9 | 74.8 | 48.8 | 52.4 | 51.8 | 101.1 | 53.3 | 46.9 | 54.7 | 45.8 | 105.0 | 108.4 | 6.5 | 44.0 |
car 11 | 66.0 | 100.0 | 43.1 | 64.8 | 100.0 | 54.8 | 60.3 | 39.4 | 100.0 | 30.8 | 100.0 | 56.7 | 34.0 | 95.3 | 100.0 | 36.3 | 46.4 |
car 12 | 41.2 | 99.6 | 26.8 | 68.3 | 75.8 | 40.3 | 45.7 | 25.1 | 97.8 | 31.9 | 96.9 | 76.1 | 93.6 | 92.6 | 50.9 | 20.9 | 35.8 |
car 13 | 39.0 | 100.0 | 27.1 | 69.4 | 69.7 | 44.9 | 40.9 | 19.3 | 100.0 | 29.4 | 100.0 | 70.2 | 100.0 | 78.4 | 100.0 | 70.4 | 36.3 |
car 14 | 100.0 | 100.0 | 41.2 | 64.5 | 100.0 | 40.5 | 44.6 | 56.2 | 15.8 | 48.9 | 63.2 | 26.3 | 35.8 | 100.0 | 100.0 | 15.2 | 42.3 |
car 15 | 100.0 | 100.0 | 62.3 | 65.9 | 100.0 | 59.6 | 63.8 | 51.7 | 100.0 | 31.3 | 69.2 | 44.4 | 21.9 | 79.6 | 100.0 | 12.9 | 51.0 |
car 16 | 37.9 | 95.5 | 25.5 | 64.3 | 63.3 | 39.8 | 36.2 | 15.4 | 78.0 | 22.4 | 71.5 | 44.8 | 54.2 | 39.5 | 42.8 | 21.7 | 33.0 |
car 17 | 99.9 | 99.8 | 69.9 | 56.2 | 99.5 | 67.7 | 68.9 | 28.3 | 60.6 | 20.7 | 76.1 | 18.1 | 11.6 | 31.0 | 92.1 | 19.1 | 57.6 |
Table 6 is also adjacency matrix, so it can be presented as the weighted complete network, where we have weighed links from each car to each car, weights are the similarity values from Table 6. This network (Fig. 2) can be used to study further similarities between brands utilizing clustering and classification methods.
Evaluating marketing efficiency over time (Ray and Desli Malmquist Index), 2017–2018
Name | TC | SEC | PEC | TFPG | First efficiency, 2017 | Second efficiency, 2018 |
---|---|---|---|---|---|---|
car 1 | 1 | 1 | 1 | 1 | 100 | 100 |
car 2 | 1 | 1 | 1 | 1 | 100 | 100 |
car 3 | 1.16 | 1 | 0.84 | 0.97 | 100 | 83.58 |
car 4 | 1.01 | 1.01 | 1 | 1.02 | 100 | 100 |
car 5 | 1 | 1 | 1 | 1 | 100 | 100 |
car 6 | 1.42 | 1 | 0.87 | 1.23 | 81.3 | 70.6 |
car 7 | 1.44 | 1 | 0.89 | 1.28 | 77.9 | 69 |
car 8 | 1.52 | 0.97 | 0.67 | 0.98 | 85.78 | 57.19 |
car 9 | 1.14 | 1.46 | 1.45 | 2.42 | 69.05 | 100 |
car 10 | 1.47 | 1 | 0.78 | 1.14 | 68.25 | 53.29 |
car 11 | 1 | 1 | 1 | 1 | 100 | 100 |
car 12 | 1.15 | 0.97 | 0.76 | 0.85 | 100 | 76.13 |
car 13 | 1 | 1 | 1 | 1 | 100 | 100 |
car 14 | 1 | 1.18 | 1 | 1.18 | 100 | 100 |
car 15 | 1 | 1 | 1 | 1 | 100 | 100 |
car 16 | 2.71 | 0.38 | 1.84 | 1.88 | 11.79 | 21.69 |
car 17 | 1.44 | 1.02 | 1.01 | 1.48 | 56.98 | 57.63 |
6 Conclusion
Using the example of spending on marketing, we demonstrated the methodological capabilities of Data Envelopment Analysis, a non-parametric and mathematically rigorous method of evaluating effectiveness of different companies relative to each other, with a variety of inputs and outputs. DEA is rarely used in applied research compared to other popular methods such as linear regression. Yet, it has a number of advantages. First, as a non-parametric method, it is free from the limiting assumptions of data independence and identical distribution. Second, it can be used for data of all types, not just scaled on an interval or ratio levels, and can be applied to any combination of such data. Third, it can take a large number of both inputs and outputs. Because in applied research a large number of studies involve multiple independent and dependent variables, often measured on different scales and with different strengths of association, the usability of DEA should not be underestimated. This method overcomes many limitations that are inherent to data in the computer science field, and we hope that researchers will take advantage of this tool to answer important questions not previously examined because of data issues.
Notes
Acknowledgements
The article was prepared within the framework of the Basic Research Program at the National Research University Higher School of Economics (HSE) and supported within the framework of a subsidy by the Russian Academic Excellence Project ‘5-100.’
References
- 1.Banker RD (1984) Estimating most productive scale size using data envelopment analysis. Eur J Oper Res 17(1):35–44Google Scholar
- 2.Banker RD, Charnes A, Cooper WW (1984) Some models for estimating technical and scale inefficiencies in data envelopment analysis. Manag Sci 30(9):1078–1092Google Scholar
- 3.Banker RD, Morey RC (1986) The use of categorical variables in data envelopment analysis. Manag Sci 32(12):1613–1627Google Scholar
- 4.Bessent A, Bessent W, Kennington J, Reagan B (1982) An application of mathematical programming to assess productivity in the Houston independent school district. Manag Sci 28(12):1355–1367CrossRefGoogle Scholar
- 5.Caves DW, Christensen LR, Erwin Diewert W (1982) The economic theory of index numbers and the measurement of input, output, and productivity. Econometrica 50(6):1393–1414. https://doi.org/10.2307/1913388CrossRefzbMATHGoogle Scholar
- 6.Charnes A, Cooper WW, Lewin AY, Seiford LM (1994) Basic DEA models. In: Data envelopment analysis: theory, methodology, and applications. Springer, Dordrecht, Netherlands, pp 23–47Google Scholar
- 7.Charnes A, Cooper WW, Rhodes E (1978) Measuring the efficiency of decision making units. Eur J Oper Res 2(6):429–444Google Scholar
- 8.Cook WD, Green RH, Zhu J (2006) Dual-role factors in data envelopment analysis. IIE Trans 38(2):105–115CrossRefGoogle Scholar
- 9.Cooper WW, Seiford LM, Zhu J (2004) Data envelopment analysis. Handbook on data envelopment analysis. Springer, Boston, MA, 1–39Google Scholar
- 10.Cooper WW, Seiford LM, Zhu J (eds) (2011) Handbook on data envelopment analysis, vol 164. Springer Science & Business MediaGoogle Scholar
- 11.Färe R, Grosskopf S, Lindgren B, Roos P (1994) Productivity developments in Swedish hospitals: a Malmquist output index approach. In: Data envelopment analysis: theory, methodology, and applications. Springer, Dordrecht, Netherlands, pp 253–272Google Scholar
- 12.Golany B, Gang Y (1997) Estimating returns to scale in DEA. Eur J Oper Res 103(1):28–37CrossRefGoogle Scholar
- 13.Goodin RE (2009) The state of the discipline, the discipline of the state. The Oxford handbook of political scienceGoogle Scholar
- 14.Khezrimotlagh D, Salleh S, Mohsenpour Z (2012) A new method in data envelopment analysis to find efficient decision making units and rank both technical efficient and inefficient DMUs together. Appl Math Sci 6(93):4609–4615Google Scholar
- 15.Khezrimotlagh D, Salleh S, Mohsenpour Z (2012) Benchmarking inefficient decision making units in DEA. J Basic Appl Sci Res 2(12):12056–12065Google Scholar
- 16.Lovell CAK, Rouse APB (2003) Equivalent standard DEA models to provide superefficiency scores. J Oper Res Soc 54(1):101–108CrossRefGoogle Scholar
- 17.Matousek J, Gärtner B (2007) Understanding and using linear programming. Springer Science & Business MediaGoogle Scholar
- 18.Muñiz MA (2002) Separating managerial inefficiency and external conditions in data envelopment analysis. Eur J Oper Res 143(3):625–643Google Scholar
- 19.Nicholson W (1985) Microeconomic theory: basic principles and extensions, 3rd edn. Dryden Press, Chicago, USAGoogle Scholar
- 20.Ray SC, Desli E (1997) Productivity growth, technical progress, and efficiency change in industrialized countries: comment. Am Econ Rev 87(5):1033–1039Google Scholar
- 21.Xue M, Harker PT (2002) Note: ranking DMUs with infeasible super-efficiency DEA models. Manag Sci 48(5):705–710CrossRefGoogle Scholar
- 22.Zhu J, Cook WD (eds) (2007) Modeling data irregularities and structural complexities in data envelopment analysis. Springer Science & Business Media, Boston, MA, USAzbMATHGoogle Scholar