DATA ENVELOPMENT ANALYSIS

This book explores data envelopment analysis, which measures firms' input-output efficiencies using mathematical programming techniques.

Using the neo-classical theory of production economics as the analytical framework, this book, first published in 2004, provides a unified and easily comprehensible, yet fairly rigorous, exposition of the core literature on data envelopment analysis (DEA) for readers based in different disciplines. The various DEA models are developed as nonparametric alternatives to the econometric models. Apart from the standard fare consisting of the basic input- and output-oriented DEA models formulated by Charnes, Cooper, and Rhodes, and Banker, Charnes, and Cooper, the book covers developments such as the directional distance function, free disposal hull (FDH) analysis, non-radial measures of efficiency, multiplier bounds, mergers and break-up of firms, and measurement of productivity change through the Malmquist total factor productivity index. The chapter on efficiency measurement using market prices provides the critical link between DEA and the neo-classical theory of a competitive firm. The book also covers several forms of stochastic DEA in detail.

1. Introduction and overview; 2. Productivity, efficiency, and data envelopment analysis; 3. Variable returns to scale: separating technical and scale efficiencies; 4. Extensions to the basic DEA models; 5. Non-radial models and Pareto-Koopmans measures of technical efficiency; 6. Efficiency measurement without convexity assumption: free disposal hull analysis; 7. Dealing with slacks: assurance region/cone ratio analysis, weak disposability, and congestion; 8. Efficiency of merger and break up of firms; 9. Efficiency analysis with market prices; 10. Nonparametric approaches to production analysis; 11. Measuring total factor productivity change over time; 12. Stochastic approaches to data envelopment analysis; 13. Looking ahead.

This 2004 book deals with the method of data envelopment analysis that uses mathematical programming techniques to obtain measures of efficiency of individual forms from their observed input and output quantities. This permits setting up realistic input-output targets for the firms' managers.