Semiparametric Regression for the Applied Econometrician: (Themes in Modern Econometrics)

This book provides an accessible collection of techniques for analyzing nonparametric and semiparametric regression models. Worked examples include estimation of Engel curves and equivalence scales, scale economies, semiparametric Cobb-Douglas, translog and CES cost functions, household gasoline consumption, hedonic housing prices, option prices and state price density estimation. The book should be of interest to a broad range of economists including those working in industrial organization, labor, development, urban, energy and financial economics. A variety of testing procedures are covered including simple goodness of fit tests and residual regression tests. These procedures can be used to test hypotheses such as parametric and semiparametric specifications, significance, monotonicity and additive separability. Other topics include endogeneity of parametric and nonparametric effects, as well as heteroskedasticity and autocorrelation in the residuals. Bootstrap procedures are provided.

Table of Contents:
List of figures and tables; Preface; 1. Introduction to differencing; 2. Background and overview; 3. Introduction to smoothing; 4. Higher-order differencing procedures; 5. Nonparametric functions of several variables; 6. Constrained estimation and hypothesis testing; 7. Index models and other semiparametric specifications; 8. Bootstrap procedures; Appendixes; References; Index.

Review :
"This outstanding textbook transforms abstract theoretical developments in nonparametric and semiparametric regression models into insightful and illuminating applications of great interest to empirical econometricians. The examples and exercises are well-crafted, and data and software code are accessible via the Internet." Ernst Berndt, MIT "Yatchew has written an exceptionally clear and accessible book. Full of applications to household consumption data, it makes an invaluable text and reference for the applied researcher." Richard Blundell, University College, London "An invaluable resource for the applied econometrician who wants to learn how to do applied nonparametric and semiparametric empirical studies. The many empirical examples as well as the theoretical development demonstrate a deep understanding of the topics covered." Jerry Hausman, MIT "This fluent book is an excellent source for learning, or updating oneas knowledge of semi- and nonparametric methods and their applications. It is a valuable addition to the existent books on these topics." Rosa Matzkin, Northwestern University "Yatchew's book is an excellent account of semiparametric regression. The material is nicely integrated by using a simple set of ideas which exploit the impact of differencing and weighting operations on the data. The empirical applications are attractive and will be extremely helpful for those encountering this material for the first time." Adrian Pagan, Australian National University "At the University of Toronto Adonis Yatchew is known for excellence in teaching. The key to this excellence is the succinct transparency of his exposition. At its best such exposition transcends the medium of presentation (either lecture or text). This monograph reflects the clarity of the authoras thinking on the rapidly expanding fields of semiparametric and nonparametric analysis. Both students and researchers will appreciate the mix of theory and empirical application." Dale Poirier, University of California, Irvine "A concise self-contained treatment of nonparametric and seminonparametric regression models and their applications in econometrics. It is written in an accessible style and provides key intuition for nonparametric and seminonparametric regression methods in a cross-sectional, essentially independently distributed, setting. Well-explained theoretical ideas are illustrated by many real-data examples and exercises, mainly from the field of applied microeconometrics." Fabio Trojani, University of St. Gallen, Journal of the American Statistician