Efficient set relations among data envelopment analysis models and resource use efficiency in manufacturing

• Main Author: Heimerman, Kathryn T
• Language: ENG
• Published: ScholarWorks@UMass Amherst 1993
• Subjects: Operations research|Mathematics|Economics
• Online Access: https://scholarworks.umass.edu/dissertations/AAI9329624

Data Envelopment Analysis (DEA) is a multi-criteria data analysis methodology introduced by Charnes, Cooper, and Rhodes in 1978. Since that time, it has proven to be a valuable analysis tool for strategic, policy, and operational decision problems. Its primary use is to conduct performance evaluations of technical, scale, and managerial efficiency. Since DEA generalizes the single-dimensional engineering and economic efficiency measure into a multi-dimensional measure, it has useful applications in engineering and economic studies. This dissertation addresses several aspects of the DEA methodology and presents original research results of both a theoretical and applied nature. Topics of the early chapters provide the reader with an intuitive understanding of DEA in addition to a finely-tuned technical understanding of the method. The later chapters build on this understanding through new theoretical results which contribute to a unifying DEA theory and through an empirical study of resource use efficiency in manufacturing. The theoretical research results give a thorough examination and specification of relationships between the economic concept of returns to scale enforced by different DEA models and variable set dimensionality. The relationships become apparent by examining properties of the set of units classified as efficient by each DEA model. These relationships are delineated, in set-theoretic terms, in a sequence of theorems with proofs. The applied research is an empirical DEA study of global resource use efficiency in international manufacturing using actual data obtained from the United Nations. By using the aggregate measure of efficiency which DEA provides, this research links multiple manufacturing outputs to consumption levels of multiple resources thereby incorporating the complexities of manufacturing environments which prior, simpler productivity analyses have been unable to capture. In particular, we analyze and interpret relationships between resource use and manufacturing efficiency. We compare performance of the manufacturing sectors in nations around the globe detecting temporal trends in efficiency, including differences in performance by economy type and by geographic location. Both the theoretical and the applied contributions presented in this dissertation are springboards to areas of future research. This dissertation concludes with mention of such possible extensions and follow-on studies.