Essays on Distance Functions and Inefficiency Measurement
Date
2018-07-11
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
This dissertation includes three essays on distance functions and inefficiency measurement. The main focus of the three essays is the measurement and determinants of technical inefficiency theoretically and empirically. Essay 1 provides an up-to-date review that focuses on research methods, including different approaches to measuring technical inefficiency using distance functions, the development of modeling technical inefficiency, and the most common econometric estimation techniques. It also provides a useful guide on when these methods can be used and how to implement them. Regarding estimation issues, I address the important issues that should be managed in future applications while estimating technical inefficiency, including violation of theoretical and econometric regularity, the inaccurate choice of functional form, ignoring the possibility of heterogeneity and heteroskedasticity, and suffering from the endogeneity problem. I also discuss different approaches to deal with these issues, as well as potentially productive areas for future research. Essay 2 derives the interactive effect between input and output technical inefficiencies theoretically using directional distance functions. This derivation solves the arbitrary decomposition of overall technical inefficiency into input and output components in previous studies. I argue that overall technical inefficiency equals the sum of input and output technical inefficiencies plus an interactive effect component which captures the interactions between them. I prove the results theoretically using exogenous and endogenous directional vectors. Essay 3 investigates the relationships among input, output, and overall technical inefficiencies empirically using US banking data set. Using Bayesian estimation with the monotonicity conditions imposed at each observation, I estimate these inefficiencies separately using directional input, output, and technology distance functions. I model the overall technical inefficiency as a linear function of input and output technical inefficiencies, and a term capturing the interactions between them. These determinants of overall technical inefficiency are estimated simultaneously with the variables that determine the frontier. I find significant evidence of the interactive effect between input and output technical inefficiencies which has a negative effect on the overall technical inefficiency. This result is robust to alternative directional vectors and model specifications, suggesting that the adjustability of both inputs and outputs is required for the improvement of efficiency.
Description
Keywords
Distance Functions, Inefficiency Measurement
Citation
Esheba, M. (2018). Essays on Distance Functions and Inefficiency Measurement (Doctoral thesis, University of Calgary, Calgary, Canada). Retrieved from https://prism.ucalgary.ca. doi:10.11575/PRISM/32405