Performance of Data Envelopment and Stochastic Frontier Models: In the Presence of Misspecification, Multicollinearity, and Outliers

The two principal and popular efficiency measurement methods are Data Envelopment Analysis (DEA) and Stochastic Frontier (SF) models. Many studies have compared DEA and SF models in empirical settings. However, there is a lack of empirical evidence in the literature about the proximity of these two models in measuring technical efficiency. The objective of this text is to evaluate the performance of DEA and SF models in the presence of model misspecification, multicollinearity, and outliers. Chapter one gives brief introduction to efficiency measurement models. Chapter two presents a thorough revision of DEA and SF models. Chapter three provides an overview model misspecification, multicollinearity, and outliers. Chapter four presents the results of Monte Carlo experiments conducted to evaluate the performance DEA and SF models in the presence of these three problems. Chapter five gives the results of efficiency analysis of wheat production in the Gezira scheme. Chapter six is devoted to the summary and conclusions. The text would serve as a good reference source to a wide audience of students, researchers and practitioners in different fields.