This course serves as an introduction to nonparametric estimation of the density, distribution, and regression functions and their uses in econometrics. The course consists of two parts: the first part covers various concepts of nonparametric estimation with a special focus on kernel estimation. In the second part, semiparametric estimation using nonparametric estimators as tools for estimating (partially) unknown density or regression functions is discussed. The properties and use of auxiliary nonparametric estimators within least squares, M-estimation, and generalized method of moments are studied theoretically and in the context of typical econometric applications.
All non-CentER students should ask formal permission from the Director of Graduate Studies in Economics BEFORE the start of the course.
Please send your request for permission including grade list, CV and motivation letter to CentER Graduate School at email@example.com. Note that asking permission is not just a formality.
A solid background in econometrics and statistics, such as Econometrics 1, 2 and 3 in the CentER Research Master Economics year 1 program
- Introduction to nonparametric estimation
- (Kernel) density estimation
- Nonparametric regression, in particular kernel regression
- Semiparametric M-estimation and GMM
- Applications of semiparametric estimators (in linear and nonlinear regression, limited dependent variable models, time series, and panel data)
Type of instructionslectures
Type of examswritten exam
- M.P. Wand and M.C. Jones, Kernel Smoothing, Chapman & Hall, London, 1995.
- J.L. Horowitz, Semiparametric and Nonparametric Methods in Econometrics, Springer, 2009.
- Q. Li and J.S. Racine, Nonparametric Econometrics: Theory and Practice, Princeton University Press, 2006.
- A. Pagan and A. Ullah, Nonparametric Econometrics, Cambridge University Press, 1999.