Showing papers by "William W. Cooper published in 1996"
TL;DR: Previously used models, such as those used to identify “allocative inefficiencies”, are extended by means of “assurance region” approaches which are less demanding in their information requirements and underlying assumptions.
Abstract: The extensions, new developments and new interpretations for DEA covered in this paper include: (1) new measures of efficiency, (2) new models and (3) new ways of implementing established models with new results and interpretations presented that include treatments of “congestion”, “returns-to-scale” and “mix” and “technical” inefficiencies and measures of efficiency that can be used to reflect all pertinent properties. Previously used models, such as those used to identify “allocative inefficiencies”, are extended by means of “assurance region” approaches which are less demanding in their information requirements and underlying assumptions. New opportunities for research are identified in each section of this chapter. Sources of further developments and possible sources for further help are also suggested with references supplied to other papers that appear in this volume and which are summarily described in this introductory chapter.
230 citations
TL;DR: DEA (Data Envelopment Analysis) models and concepts are formulated here in terms of the "P-Models" of Chance Constrained Programming, which are modified to contact the "satisficing concepts" of H.A. Simon, adding as a third category to the efficiency/inefficiency dichotomies that have heretofore prevailed in DEA.
Abstract: DEA (Data Envelopment Analysis) models and concepts are formulated here in terms of the “P-Models” of Chance Constrained Programming, which are then modified to contact the “satisficing concepts” of H.A. Simon. Satisficing is thereby added as a third category to the efficiency/inefficiency dichotomies that have heretofore prevailed in DEA. Formulations include cases in which inputs and outputs are stochastic, as well as cases in which only the outputs are stochastic. Attention is also devoted to situations in which variations in inputs and outputs are related through a common random variable. Extensions include new developments in goal programming with deterministic equivalents for the corresponding satisficing models under chance constraints.
217 citations
TL;DR: In this paper, the authors discuss alternative methods for determining returns to scale in DEA, based on Banker's concept of Most Productive Scale Size (MPSS), which is equivalent to the two-stage methods of Fare, Grosskopf and Lovell.
139 citations
TL;DR: Banker and Thrall as discussed by the authors modified one of their suggestions to avoid the need for examining all alternate optima in order to reach a decision, adding computational convenience and efficiency to the article.
109 citations
TL;DR: In this article, a mixed integer programming model is proposed to restrict the efficiency evaluations to comparisons with observed performances, while retaining the ability to identify the sources and amounts of inefficiency in each DMU that is evaluated.
Abstract: The usual models in DEA (Data Envelopment Analysis) employ a postulate of continuity to obtain comparison points for the entities known as DMus (Decision Making Units) whose input-output behavior is to be evaluated. In some applications, it may be desired to restrict attention to actual DMus and hence to drop (or modify) the continuity assumptions in DEA. Using the concept of efficiency dominance, this is accomplished in the present paper in the form of mixed integer programming models which restrict the efficiency evaluations to comparisons with actually observed performances. Simple and easily interpreted scalar measures of efficiency are provided while retaining the ability to identify the sources and amounts of inefficiency in each DMU that is evaluated.
104 citations
TL;DR: In evaluating efficiency, DEA generally shows superior performance, with BCC models being best (except at “corner points”), followed by the CCR model and then by COLS, with log-linear regressions performing better than their translog counterparts at almost all sample sizes.
Abstract: Using statistically designed experiments, 12,500 observations are generated from a “4-pieced Cobb-Douglas function” exhibiting increasing and decreasing returns to scale in its different pieces. Performances of DEA and frontier regressions represented by COLS (Corrected Ordinary Least Squares) are compared at sample sizes ofn=50, 100, 150 and 200. Statistical consistency is exhibited, with performances improving as sample sizes increase. Both DEA and COLS generally give good results at all sample sizes. In evaluating efficiency, DEA generally shows superior performance, with BCC models being best (except at “corner points”), followed by the CCR model and then by COLS, with log-linear regressions performing better than their translog counterparts at almost all sample sizes. Because of the need to consider locally varying behavior, only the CCR and translog models are used for returns to scale, with CCR being the better performer. An additional set of 7,500 observations were generated under conditions that made it possible to compare efficiency evaluations in the presence of collinearity and with model misspecification in the form of added and omitted variables. Results were similar to the larger experiment: the BCC model is the best performer. However, COLS exhibited surprisingly good performances — which suggests that COLS may have previously unidentified robustness properties — while the CCR model is the poorest performer when one of the variables used to generate the observations is omitted.
76 citations
TL;DR: New combinations of Data Envelopment Analysis (DEA) and statistical approaches that can be used to evaluate efficiency within a multiple-input multiple-output framework are examined, consistent with what might be expected from economic theory and informative for educational policy uses.
Abstract: This paper examines new combinations of Data Envelopment Analysis (DEA) and statistical approaches that can be used to evaluate efficiency within a multiple-input multiple-output framework. Using data on five outputs and eight inputs for 638 public secondary schools in Texas, unsatisfactory results are obtained initially from both Ordinary Least Squares (OLS) and Stochastic Frontier (SF) regressions run separately using one output variable at-a-time. Canonical correlation analysis is then used to aggregate the multiple outputs into a single “aggregate” output, after which separate regressions are estimated for the subsets of schools identified as efficient and inefficient by DEA. Satisfactory results are finally obtained by a joint use of DEA and statistical regressions in the following manner. DEA is first used to identify the subset of DEA-efficient schools. The entire collection of schools is then comprehended in a single regression with dummy variables used to distinguish between DEA-efficient and DEA-inefficient schools. The input coefficients are positive for the efficient schools and negative and statistically significant for the inefficient schools. These results are consistent with what might be expected from economic theory and are informative for educational policy uses. They also extend the treatments of production functions usually found in the econometrics literature to obtain one regression relation that can be used to evaluate both efficient and inefficient behavior.
68 citations
TL;DR: In this paper, the authors examined models and measures of efficiency dominance as treated by Free Disposal Hull and Russell Measure approaches to efficiency evaluation as they relate to additive models and MED (Measures of Efficiency Dominance) in DEA.
Abstract: Models and measures of efficiency dominance as treated by Free Disposal Hull and Russell Measure approaches to efficiency evaluation are examined as they relate to additive models and MED (Measures of Efficiency Dominance) in DEA.
41 citations
TL;DR: The results of tests show that TNDE as a single aggregate measure of plant output outperforms the two outputs from which it is synthesized, demonstrating how DEA concepts and models provide a rigorous and systematic basis for conducting ex post technology evaluation to guide continuous improvements in a plant's current operations.
Abstract: Commonly used measures of plant output have been criticized for their inability to provide information required to manage the dynamic operations of high-technology manufacturing plants. In this paper, we propose tests to evaluate the information content of a measure of plant output that is specifically directed at these issues. These tests are based on recent developments in DATA Envelopment Analysis (DEA), namely the Cone Ratio Envelopments. In this new application of DEA models, we shift the focus from Decision Making Units (DMUs) being evaluated to the DMUs that are being used to effect evaluations. The proposed tests are applied to evaluate the information contnet of a complexity adjusted measure of plant output, which we refer to as Total Net Die Equivalent (TNDE). Developed recently in the context of a high-technology manufacturing plant—a wafer fabrication plant of a merchant semiconductor manufacturing company-TNDE reflects the ongoing changes in product and process technologies, process flow characteristics, and volume of production. Evaluating the information content on joint criteria of “recency” and “efficiency”, the results of our tests, conducted over a 28-month period in the wafer fabrication plant,show that TNDE as a single aggregate (scalar) measure of plant output outperforms the two outputs from which it is synthesized. Thus, TNDE as a single measure of output can be used to provide an improved basis for planning a plant's future operations. En route to the development and application of the proposed tests, we illustrate how DEA concepts and models provide a rigorous and systematic basis for conducting ex post technology evaluation to guide continuous improvements in a plant's current operations.
16 citations