Data Envelopment Analysis: A Nonparametric Method of Production Analysis

In the Operations Research/Management Science literature, the nonparametric method of Data Envelopment Analysis (DEA) has gained wide popularity as a valid analytical format for efficiency evaluation. In economics, however, its reception has been far less enthusiastic. Yet, the intellectual roots of DEA go back to the seminal contributions to nonparametric analysis of production by Debreu, Shephard, Farrell, Afriat, and others. Over the past four decades, DEA has matured into a full blown non-parametric methodology for measuring productive efficiency that serves as an alternative to parametric Stochastic Frontier Analysis (SFA). Both grounded into the neoclassical theory of production, DEA and SFA provide the researcher alternative ways to calibrate testable relations between inputs, outputs, costs, revenue, and profit. Staring from the central concept of the Production Possibility set, this chapter provides a broad overview of the literature on DEA methodology for radial and non-radial measurement of technical efficiency from input and output quantity data under alternative returns to scale assumptions. This is followed by models for performance evaluation in the presence of market prices through cost, revenue, and overall profit efficiency- both in the long run when all inputs are variable and in the short run, when some inputs are fixed. DEA models for physical measures of the capacity output in the short run and economic measures of capacity in the long run are discussed. Alternative ways to incorporate the production of ‘bad’ or undesirable outputs collaterally with the ‘good’ or intended output in DEA models for efficiency measurement are presented. Finally, the role of contextual or environmental variables that affect efficiency is also discussed.