Search

This paper surveys recently developed analytical methods for studying the sensitivity of DEA results to variations in the data. The focus is on the stability of classification of DMUs (Decision Making Units) into efficient and inefficient performers. Early work on this topic concentrated on developing solution methods and algorithms for conducting such analyses after it was noted that standard approaches for conducting sensitivity analyses in linear programming could not be used in DEA. However, some of the recent work we cover has bypassed the need for such algorithms. Evolving from early work that was confined to studying data variations in only one input or output for only one DMU at a time, the newer methods described in this paper make it possible to determine ranges within which all data may be varied for any DMU before a reclassification from efficient to inefficient status (or vice versa) occurs. Other coverage involves recent extensions which include methods for determining ranges of data variation that can be allowed when all data are varied simultaneously for all DMUs. An initial section delimits the topics to be covered. A final section suggests topics for further research. [ABSTRACT FROM AUTHOR]

Marginal rates and elasticities of substitution are derived from the optimal slack values obtained from modified versions of additive DEA models. Projection formulas are used to ensure that all points are on the efficient frontier as required for conformance with assumptions in micro-economics. The models used differ from standard versions in that slack values are allowed to be negative as well as positive in these additive models. This makes movement possible on efficiency frontiers, where improvement in some inputs or outputs requires worsening other inputs or outputs. A new definition is therefore introduced in which efficiency is attained only if the value of the worsenings is exactly offset by the value of the improvements. This includes, but is not restricted to, the case in which all slacks must be zero for full attaimnent of efficiency-as in standard versions of additive models. [ABSTRACT FROM AUTHOR]

A model for measuring the efficiency of Decision Making Units (= DMU's) is presented, along with related methods of implementation and interpretation. The term DMU is intended to emphasize an orientation toward managed entities in the public and/or not-for-profit sectors. The proposed approach is applicable to the multiple outputs and designated inputs which are common for such DMU's. A priori weights, or imputations of a market-price-value character are not required. A mathematical programming model applied to observational data provides a new way of obtaining empirical estimates of extremal relations -- such as the production functions and/or efficient production possibility surfaces that are a cornerstone of modern economics. The resulting extremal relations are used to envelop the observations in order to obtain the efficiency measures that form a focus of the present paper. An illustrative application utilizes data from Program Follow Through (= PFT). A large scale social experiment in public school education, it was designed to test the advantages of PFT relative to designated NFT (= Non-Follow Through) counterparts in various parts of the U.S. It is possible that the resulting observations are contaminated with inefficiencies due to the way DMU's were managed en route to assessing whether PFT (as a program) is superior to its NFT alternative. A further mathematical programming development is therefore undertaken to distinguish between "management efficiency" and "program efficiency." This is done via procedures referred to as Data Envelopment Analysis (= DEA) in which one first obtains boundaries or envelopes from the data for PFT and NFT, respectively. These boundaries provide a basis for estimating the relative efficiency of the DMU's operating under these programs. These DMU's are then adjusted up to their program boundaries, after which a new inter-program envelope is obtained for evaluating the PFT and NFT programs with the estimated managerial inefficiencies eliminated. The claimed superiority of PFT fails to be validated in this illustrative application. Our DEA approach, however, suggests the additional possibility of new approaches obtained from PFT-NFT combinations which may be superior to either of them alone. Validating such possibilities cannot be done only by statistical or other modelings. It requires recourse to field studies, including audits (e.g., of a U.S. General Accounting Office variety) and therefore ways in which the results of a DEA approach may be used to guide such further studies (or audits) are also indicated. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

This article presents a study which examined sensitivity and stability analysis in data envelopment analysis. Sensitivity analyses is regarded as a mathematical programming counterpart of significance testing in statistics since each is concerned with examining allowable ranges of variation in the data.

This paper serves as an introduction to a series of three papers which are directed to different aspects of DEA (Data Envelopment Analysis) as follows: (1) uses and extensions of 'window analyses' to study DEA efficiency measures with an illustrative applications to maintenance activities for U.S. Air Force fighter wings, (2) a comparison of DEA and regression approaches to identifying and estimating sources of inefficiency by means of artificially generated data, and (3) an extension of ordinary (linear programming) sensitivity analyses to deal with special features that require attention in DEA. Background is supplied in this introductory paper with accompanying proofs and explanations to facilitate understanding of what DEA provides in the way of underpinning for the papers that follow. An attempt is made to bring readers abreast of recent progress in DEA research and uses. A synoptic history is presented along with brief references to related work, and problems requiring attention are also indicated and possible research approaches also suggested. [ABSTRACT FROM AUTHOR]

This paper shows that the Lagrange multiplier method suggested by H. Everett does not have 'Fail-Safe' properties when applied to simple situations with nonconvexity only in the functional. Although each Lagrange multiplier problem for these situations has immediate solutions no means of combining them to obtain a solution to any reasonable approximation appears to be visible. [ABSTRACT FROM AUTHOR]

Several letters to the editor are presented in response to the articles "Management Models and Industrial Applications of Linear Programming," published in the October 1957 issue and "A Linear Decision Rule For Production And Employment Scheduling," published in the October 1955 issue.