Nonparametric Measurement of Productivity Growth and Technical Change explains how to isolate technical progress, scale effects, and efficiency changes as three distinct components of productivity change measured empirically using the nonparametric method of Data Envelopment Analysis (DEA). Section 2 provides a brief theoretical background, starting from the production possibility set, listing the basic assumptions about the reference technology, and defining the Shephard output and input distance functions, as well as technical change as shifts in the frontier of the production possibility set. Section 3 demonstrates how total factor productivity can be measured and decomposed into technical change, technical efficiency change, and scale effects using parametrically specified production, cost, profit, or distance functions. Section 4 explains the nonparametric method of DEA and formulates appropriate models for measuring input- or output-oriented technical efficiency, cost efficiency, and profit efficiency. Section 5 considers productivity change in discrete time. Section 6 explains the relationship between alternative productivity indexes and the Luenberger productivity indicator. Finally, Section 7 concludes with a summary and acknowledges several important topics related to the nonparametric measurement of productivity change not covered in this monograph, including the explicit accommodation of random noise in the DEA models, accounting for bad outputs, and the aggregation of firm-level measures of productivity change for comparison across groups.
Nonparametric Measurement of Productivity Growth and Technical Change explains how to isolate technical progress, scale effects, and efficiency changes as three distinct components of productivity change measured empirically using the nonparametric method of Data Envelopment Analysis (DEA). Section 2 provides a brief theoretical background, starting from the production possibility set, listing the basic assumptions about the reference technology, and defining the Shephard output and input distance functions, as well as technical change as shifts in the frontier of the production possibility set. Section 3 demonstrates how total factor productivity can be measured and decomposed into technical change, technical efficiency change, and scale effects using parametrically specified production, cost, profit, or distance functions. Section 4 explains the nonparametric method of DEA and formulates appropriate models for measuring input- or output-oriented technical efficiency, cost efficiency, and profit efficiency. Section 5 considers productivity change in discrete time. Section 6 explains the relationship between alternative productivity indexes and the Luenberger productivity indicator. Finally, Section 7 concludes with a summary and acknowledges several important topics related to the nonparametric measurement of productivity change not covered in this monograph, including the explicit accommodation of random noise in the DEA models, accounting for bad outputs, and the aggregation of firm-level measures of productivity change for comparison across groups.
