1;Handbook on Data Envelopment Analysis;3 1.1;Preface;7 1.2;About the Authors;11 1.3;Contents;21 1.4;Contributors;23 1.5;Chapter 1: Data Envelopment Analysis: History, Models, and Interpretations
     ;27 1.5.1;1.1 Introduction;27 1.5.2;1.2 Background and History;29 1.5.3;1.3 CCR Model;33 1.5.4;1.4 Extensions to the CCR Model;44 1.5.4.1;1.4.1 Nondiscretionary Inputs and Outputs;44 1.5.4.2;1.4.2 Categorical Inputs and Outputs;46 1.5.4.3;1.4.3 Incorporating Judgment or A Priori Knowledge;47 1.5.4.4;1.4.4 Window Analysis;49 1.5.5;1.5 Allocative and Overall Efficiency;52 1.5.6;1.6 Profit Efficiency;55 1.5.7;1.7 Recent Developments;60 1.5.8;1.8 Conclusions;62 1.5.9;References;62 1.6;Chapter 2: Returns to Scale in DEA
    ;66 1.6.1;2.1 Introduction;66 1.6.2;2.2 RTS Approaches with BCC Models;68 1.6.3;2.3 RTS Approaches with CCR Models;73 1.6.4;2.4 Most Productive Scale Size;79 1.6.5;2.5 Additive Models;82 1.6.6;2.6 Multiplicative Models;86 1.6.7;2.7 Summary and Conclusion;91 1.6.8;Appendix;93 1.6.9;References;94 1.7;Chapter 3: Sensitivity Analysis in DEA
    ;96 1.7.1;3.1 Introduction;96 1.7.2;3.2 Sensitivity Analysis Approaches;97 1.7.2.1;3.2.1 Algorithmic Approaches;98 1.7.2.2;3.2.2 Metric Approaches;98 1.7.2.3;3.2.3 Multiplier Model Approaches;102 1.7.2.4;3.2.4 A Two-Stage Alternative;106 1.7.2.5;3.2.5 Envelopment Approach;109 1.7.3;3.3 Summary and Conclusion;115 1.7.4;References;115 1.8;Chapter 4: Choices and Uses of DEA Weights;117 1.8.1;4.1 Introduction;117 1.8.2;4.2 Using Price Information;120 1.8.3;4.3 Reflecting Meaningful Trade-Offs;122 1.8.4;4.4 Incorporating Value Information and Managerial Goals;125 1.8.5;4.5 Choosing From Alternate Optima;129 1.8.6;4.6 Looking for Non-zero Weights;133 1.8.7;4.7 Avoiding Large Differences in the Values of Multipliers;136 1.8.8;4.8 Improving Discrimination and Ranking Units;139 1.8.9;4.9 Conclusions;144 1.8.10;References;146 1.9;Chapter 5: Malmquist Productivity Indexes and DEA;151 1.9.1;5.1 Introduction;151 1.9.2;5.2 DEA Technologies;152 1.9.3;5.3 Projecting onto the Frontier;156 1.9.4;5.4 Productivity Indexes;162 1.9.5;5.5 A Dynamic Malmquist Productivity Index;170 1.9.6;References;172 1.10;Chapter 6: Qualitative Data in DEA;174 1.10.1;6.1 Introduction;174 1.10.2;6.2 Problem Settings Involving Ordinal Data;175 1.10.2.1;6.2.1 Ordinal Data in RandD Project Selection;175 1.10.2.2;6.2.2 Efficiency Performance of Korean Telephone Offices;177 1.10.3;6.3 Modeling Ordinal Data;179 1.10.3.1;6.3.1 Permissible Worth Vectors;182 1.10.3.2;6.3.2 Criteria Importance;186 1.10.4;6.4 Solutions to Applications;187 1.10.4.1;6.4.1 RandD Project Efficiency Evaluation;187 1.10.4.2;6.4.2 Evaluation of Telephone Office Efficiency;188 1.10.5;6.5 Problem Settings and Issues Involving Qualitative Data;189 1.10.5.1;6.5.1 Implementation of Robotics: Identifying Efficient Implementers;190 1.10.5.2;6.5.2 A Fair Model for Aggregating Preferential Votes;190 1.10.5.3;6.5.3 Multiple Criteria Decision Modeling: Ordinal Data, Criteria Importance, and Criteria Clearness;191 1.10.5.3.1;6.5.3.1 Evaluating Vendors for Complex Systems;192 1.10.5.3.2;6.5.3.2 Country Risk Evaluation;192 1.10.5.3.3;6.5.3.3 Mutual Fund Selection;193 1.10.5.3.4;6.5.3.4 Ordinal Data in Multicriteria Modeling: Evaluation in Terms of Subsets of Criteria;193 1.10.6;6.6 Discussion;194 1.10.7;References;194 1.11;Chapter 7: Congestion: Its Identification and Management with DEA;196 1.11.1;7.1 Congestion;196 1.11.2;7.2 Comparison of Two Literatures on Congestion;201 1.11.3;7.3 Färe, Grosskopf, and Lovell (FGL) Approach;201 1.11.4;7.4 Cooper, Thompson, and Thrall (CTT) Approach;205 1.11.4.1;7.4.1 A Numerical Example;207 1.11.5;7.5 A Unified Additive Model;209 1.11.6;7.6 Estimating the Output Effects of Congestion;211 1.11.7;7.7 Extensions;214 1.11.8;References;215 1.12;Chapter 8: Slacks-Based Measure of Efficiency;217 1.12.1;8.1 Introduction;217 1.12.2;8.2 The SBM Model;218 1.12.2.1;8.2.1 Production Possibility Set;218 1.12.2.2;8.2.2 Input-Oriented SBM;219 1.12.2.3;8.2.3 Output-Oriented SBM;220 1.12.2.4;8.2.4 Nonoriented SBM;221 1.12.2.5;8.2.5 An Illustrative Example of SBM Models;222 1.12.2.6;8.2.6 The Dual Program of the SBM Model;223 1.12.3;8.3 Extensions of the SBM Model;224 1.12.3.1;8.3.1 Variable Returns-to-Scale Model;224 1.12.3.2;8.3.2 Weighted-SBM Model;225 1.12.3.3;8.3.3 Super-SBM Model;226 1.12.3.4;8.3.4 An Illustrative Example of Super-SBM Models;227 1.12.4;8.4 Further Extensions;227 1.12.4.1;8.4.1 Dealing with Nonpositive Data in the SBM Models;227 1.12.4.2;8.4.2 Variations of the SBM Models;229 1.12.4.3;8.4.3 A Compromise of Radial and Nonradial Measures of Efficiency;230 1.12.5;8.5 Concluding Remarks;230 1.12.6;References;231 1.13;Chapter 9: Chance-Constrained DEA;232 1.13.1;9.1 Introduction;232 1.13.2;9.2 Efficiency and Efficiency Dominance;233 1.13.3;9.3 Stochastic Dominance and Joint Chance Constrained Efficiency;236 1.13.3.1;9.3.1 Potential Uses;239 1.13.4;9.4 Stochastic Efficiency in Marginal Chance Constrained Models;244 1.13.5;9.5 Satisficing DEA Models;252 1.13.6;9.6 Concluding Remarks;258 1.13.7;References;259 1.14;Chapter 10: Performance of the Bootstrap for DEA Estimators and Iterating the Principle;262 1.14.1;10.1 Introduction;262 1.14.2;10.2 Efficiency and the Theory of the Firm;263 1.14.3;10.3 Estimation;265 1.14.4;10.4 A Statistical Model;268 1.14.5;10.5 Some Asymptotic Results;269 1.14.6;10.6 Bootstrapping in DEA/FDH Models;271 1.14.7;10.7 Implementing the Bootstrap;274 1.14.8;10.8 Monte Carlo Evidence;279 1.14.9;10.9 Enhancing the Performance of the Bootstrap;287 1.14.10;10.10 Conclusions;289 1.14.11;References;290 1.15;Chapter 11: Statistical Tests Based on DEA Efficiency Scores;293 1.15.1;11.1 Introduction;293 1.15.2;11.2 Hypothesis Tests When Inefficiency is the Only Stochastic Variable;295 1.15.2.1;11.2.1 Statistical Foundation for DEA;295 1.15.2.2;11.2.2 Efficiency Comparison of Two Groups of DMUs;296 1.15.2.3;11.2.3 Tests of Returns to Scale;297 1.15.2.4;11.2.4 Tests of Allocative Efficiency;299 1.15.2.5;11.2.5 Tests of Input Separability;301 1.15.3;11.3 Hypothesis Tests for Situations Characterized by Shifts in Frontier;302 1.15.4;11.4 Hypothesis Tests for Composed Error Situations;306 1.15.4.1;11.4.1 Tests for Efficiency Comparison;307 1.15.4.2;11.4.2 Tests for Evaluating the Impact of Contextual Variables on Efficiency;308 1.15.4.3;11.4.3 Tests for Evaluating the Adequacy of Parametric Functional Forms;311 1.15.5;11.5 Concluding Remarks;313 1.15.6;References;314 1.16;Chapter 12: Modeling DMU´s Internal Structures: Cooperative and Noncooperative Approaches;316 1.16.1;12.1 Introduction;316 1.16.2;12.2 Two-Stage Processes;318 1.16.3;12.3 Centralized Model;319 1.16.4;12.4 Stackelberg Game;322 1.16.5;12.5 DEA Model for General Multistage Serial Processes Via Additive Efficiency Decomposition;325 1.16.6;12.6 General Multistage Processes;328 1.16.6.1;12.6.1 Parallel Processes;328 1.16.6.2;12.6.2 Nonimmediate Successor Flows;329 1.16.7;12.7 Conclusions;330 1.16.8;References;331 1.17;Chapter 13: Assessing Bank and Bank Branch Performance;333 1.17.1;13.1 Introduction;333 1.17.2;13.2 Performance Measurement Approaches in Banking;334 1.17.2.1;13.2.1 Ratio Analysis;334 1.17.2.2;13.2.2 Frontier Efficiency Methodologies;335 1.17.2.3;13.2.3 Other Performance Evaluation Methods;336 1.17.3;13.3 Data Envelopment Analysis in Banking;336 1.17.3.1;13.3.1 Banking Corporations;337 1.17.3.1.1;13.3.1.1 In-Country;337 1.17.3.1.2;13.3.1.2 Cross-Country Studies;338 1.17.3.2;13.3.2 Bank Branches;339 1.17.3.2.1;13.3.2.1 Small Number of Branches;339 1.17.3.2.2;13.3.2.2 Large Number of Branches;340 1.17.3.2.3;13.3.2.3 Branch Studies Incorporating Service Quality;341 1.17.3.2.4;13.3.2.4 Unusual Banking Applications of DEA;341 1.17.4;13.4 Model Building Considerations;342 1.17.4.1;13.4.1 Approaching the Problem;342 1.17.4.2;13.4.2 Input or Output?;342 1.17.4.3;13.4.3 Too Few DMUs/Too Many Variables;343 1.17.4.4;13.4.4 Relationships and Proxies;344 1.17.4.5;13.4.5 Outliers;344 1.17.4.6;13.4.6 Zero or Blank?;345 1.17.4.7;13.4.7 Size Does Matter;345 1.17.4.8;13.4.8 Too Many DMUs on the Frontier;346 1.17.4.9;13.4.9 Environmental Factors;346 1.17.4.10;13.4.10 Service Quality;347 1.17.4.11;13.4.11 Validating Results;347 1.17.5;13.5 Banks as DMUS;347 1.17.5.1;13.5.1 Cross-Country/Region Comparisons;348 1.17.5.2;13.5.2 Bank Mergers;349 1.17.5.2.1;13.5.2.1 Selecting Pairs of Branch Units for Merger Evaluation;351 1.17.5.2.2;13.5.2.2 Defining a Strategy for Hypothetically Merging Two Bank Branches;351 1.17.5.2.3;13.5.2.3 Developing Models for Evaluating the Overall Performance of Merged Units Through the Selection of Appropriate Input and Output Variables ;352 1.17.5.2.4;13.5.2.4 Calculating Potential Efficiency Gains;352 1.17.5.2.5;13.5.2.5 Identifying Differences in Cultural Environments Between the Merging Banks;352 1.17.5.2.6;13.5.2.6 Calculating Potential Synergies;353 1.17.5.3;13.5.3 Temporal Studies;354 1.17.5.3.1;13.5.3.1 The Models;354 1.17.5.3.2;13.5.3.2 Window Analysis;355 1.17.5.3.3;13.5.3.3 Malmquist Productivity Index;357 1.17.6;13.6 Bank Branches as DMUS;361 1.17.6.1;13.6.1 The Production Model;362 1.17.6.2;13.6.2 Profitability Model;363 1.17.6.3;13.6.3 Intermediation Model;364 1.17.6.4;13.6.4 Model Results;365 1.17.6.5;13.6.5 Senior Management Concerns;366 1.17.6.6;13.6.6 A Two-Stage Process;367 1.17.6.7;13.6.7 Targeted Analysis;368 1.17.6.8;13.6.8 New Role of Bank Branch Analysis;369 1.17.6.9;13.6.9 Environmental Effects;370 1.17.7;13.7 Validation;372 1.17.7.1;13.7.1 Validating a Method with Monte Carlo Simulation;372 1.17.8;13.8 Conclusions;373 1.17.9;References;374 1.18;Chapter 14: Engineering Applications of Data Envelopment Analysis;380 1.18.1;14.1 Background and Context;381 1.18.2;14.2 Research Issues and Opportunities;384 1.18.2.1;14.2.1 Evaluating Design Alternatives;384 1.18.2.2;14.2.2 Disaggregated Process Evaluation and Improvement: Opening the ``Input/Output Transformation Box´´;385 1.18.2.3;14.2.3 Hierarchical Manufacturing System Performance;386 1.18.2.4;14.2.4 Data Measurement Imprecision in Production Systems;389 1.18.2.5;14.2.5 Dynamical Production Systems;391 1.18.2.6;14.2.6 Visualization of the DEA Results: Influential Data Identification;395 1.18.3;14.3 A DEA-Based Approach Used for the Design of an Integrated Performance Measurement System;396 1.18.4;14.4 Selected DEA Engineering Applications;399 1.18.4.1;14.4.1 Four Applications;399 1.18.4.1.1;14.4.1.1 Evaluating Efficiency of Turbofan Jet Engines (Bulla et al. 2000);399 1.18.4.1.2;14.4.1.2 Measurement and Monitoring of Relative Efficiency of Highway Maintenance Patrols (Cook et al. 1990, 1994) and of Highway Maintenance Operations (Ozbek et al. 2010a, b)6 ;400 1.18.4.1.3;14.4.1.3 Data Envelopment Analysis of Space and Terrestrially Based Large Scale Commercial Power Systems for Earth (Criswell and Thompson 1996) ;401 1.18.4.1.4;14.4.1.4 The Relationship of DEA and Control Charts (Hoopes and Triantis 2001);401 1.18.4.2;14.4.2 The Effect of Environmental Controls on Productive Efficiency;402 1.18.4.3;14.4.3 The Performance of Transit Systems;403 1.18.4.4;14.4.4 Other Engineering Applications of DEA;404 1.18.5;14.5 Systems Thinking Concepts and Future DEA Research in Engineering;405 1.18.5.1;14.5.1 The Need for Operational Thinking;405 1.18.5.2;14.5.2 Contribution to Performance Measurement Science;406 1.18.5.3;14.5.3 Relationship of the DEA Model with the Real World;407 1.18.6;References;408 1.19;Chapter 15: Applications of Data Envelopment Analysis in the Service Sector;420 1.19.1;15.1 Introduction;420 1.19.2;15.2 Universities1 ;423 1.19.2.1;15.2.1 Introduction;423 1.19.2.2;15.2.2 Conceptual Framework;424 1.19.2.3;15.2.3 Research Design;426 1.19.2.4;15.2.4 Results and Analysis;428 1.19.2.5;15.2.5 Concluding Remarks;429 1.19.3;15.3 Hotels2 ;430 1.19.3.1;15.3.1 Introduction;430 1.19.3.2;15.3.2 Conceptual Framework;431 1.19.3.3;15.3.3 A Quick Guide to Selecting Inputs and Outputs;433 1.19.3.4;15.3.4 A Numerical Example;433 1.19.3.5;15.3.5 Concluding Remarks;435 1.19.4;15.4 Real Estate Agents3 ;436 1.19.4.1;15.4.1 Introduction;436 1.19.4.2;15.4.2 Research Design;437 1.19.4.3;15.4.3 Analysis of Results;439 1.19.4.4;15.4.4 Concluding Remarks;441 1.19.5;15.5 Commercial Banks5 ;442 1.19.5.1;15.5.1 Introduction;442 1.19.5.2;15.5.2 Conceptual Framework;443 1.19.5.2.1;15.5.2.1 Modeling Profit Efficiency;443 1.19.5.2.2;15.5.2.2 Key Profit Centers and Estimating Corresponding Data;444 1.19.5.3;15.5.3 Methodology;446 1.19.5.3.1;15.5.3.1 Overview of Network DEA;446 1.19.5.3.2;15.5.3.2 Network Slacks-Based Measure of Efficiency;449 1.19.5.3.3;15.5.3.3 Data and Simulation;450 1.19.5.4;15.5.4 Results and Analysis;451 1.19.5.4.1;15.5.4.1 Profit Efficiency Using Traditional DEA (SBM);451 1.19.5.4.2;15.5.4.2 Profit Efficiency Using Network SBM and Simulated Profit Center Data;452 1.19.5.5;15.5.5 Concluding Remarks;454 1.19.6;15.6 Epilogue;455 1.19.7;References;457 1.20;Chapter 16: Health-Care Applications: From Hospitals to Physicians, from Productive Efficiency to Quality Frontiers;461 1.20.1;16.1 Introduction;461 1.20.2;16.2 Brief Background and History;463 1.20.2.1;16.2.1 Acute General Hospitals and Academic Medical Centers;464 1.20.2.2;16.2.2 Nursing Homes;465 1.20.2.3;16.2.3 Department Level, Team-Level, and General Health-Care Studies;466 1.20.2.4;16.2.4 Physician-Level Studies;467 1.20.2.5;16.2.5 Data Envelopment Analysis Versus Stochastic Frontier Analysis;468 1.20.2.6;16.2.6 Reviewer Comments on the Usefulness of DEA;469 1.20.2.7;16.2.7 Summary;470 1.20.3;16.3 Health-Care Models;471 1.20.3.1;16.3.1 Clinical Efficiency Definitions;471 1.20.3.2;16.3.2 How to Model Health-Care Providers: Hospitals, Nursing Homes, Physicians;472 1.20.3.3;16.3.3 Managerial and Clinical Efficiency Models;473 1.20.3.3.1;16.3.3.1 Medical Center and Acute Hospital Models: Examples of Managerial Efficiency;475 1.20.3.3.2;16.3.3.2 Nursing Homes: Another Example of Managerial Efficiency;476 1.20.3.3.3;16.3.3.3 Primary Care Physician Models: An Example of Clinical Efficiency;477 1.20.3.4;16.3.4 Hospital Physician Models: Another Example of Clinical Efficiency;478 1.20.3.5;16.3.5 Profitability Models: A Nursing Home Example;479 1.20.4;16.4 Special Issues for Health Applications;481 1.20.4.1;16.4.1 Defining Models from Stakeholder Views;481 1.20.4.2;16.4.2 Selecting Appropriate Health-Care Outputs and Inputs: The Greatest Challenge for DEA;483 1.20.4.2.1;16.4.2.1 Take Two Aspirin and Call Me in the Morning;483 1.20.4.2.2;16.4.2.2 Using DEA to Adjust Outputs for Patient Characteristics and Case mix;484 1.20.4.3;16.4.3 Should Environmental and Organizational Factors Be Used as Inputs?;485 1.20.4.4;16.4.4 Problems on the Best Practice Frontier: A Physician Example;485 1.20.4.4.1;16.4.4.1 The Concept of a Preferred Practice Cone or Quality Assurance Region;487 1.20.4.4.2;16.4.4.2 Constant Versus Variable Returns to Scale;488 1.20.4.4.3;16.4.4.3 Scale and Scope Issues;489 1.20.4.5;16.4.5 Analyzing DEA Scores with Censored Regression Models;489 1.20.5;16.5 New Directions: From Productive Efficiency Frontiers to Quality-Outcome Frontiers;492 1.20.5.1;16.5.1 A Field Test: Combining Outcome Frontiers and Efficiency Frontiers;495 1.20.6;16.6 A Health DEA Application Procedure: Eight Steps;497 1.20.6.1;16.6.1 Step 1: Identification of Interesting Health-Care Problem and Research Objectives;497 1.20.6.2;16.6.2 Step 2: Conceptual Model of the Medical Care Production Process;498 1.20.6.3;16.6.3 Step 3: Conceptual Map of Factors Influencing Care Production;498 1.20.6.4;16.6.4 Step 4: Selection of Factors;498 1.20.6.5;16.6.5 Step 5: Analyze Factors Using Statistical Methods;499 1.20.6.6;16.6.6 Step 6: Run Several DEA Models;499 1.20.6.7;16.6.7 Step 7: Analyze DEA Scores with Statistical Methods;499 1.20.6.8;16.6.8 Step 8: Share Results with Practitioners and Write It Up;500 1.20.7;16.7 DEA Health Applications: Do´s and Don´ts;500 1.20.7.1;16.7.1 Almost Never Include Physicians As a Labor Input;500 1.20.7.2;16.7.2 Use Caution When Modeling Intermediate and Final Hospital Outputs;501 1.20.7.3;16.7.3 Do Check the Distribution of DEA Scores and Influence of Best Practice Providers on Reference Sets;503 1.20.8;16.8 A Final Word;504 1.20.9;References;506 1.21;Index;510