ECON 6990

Topics in Econometric Theory: Nonparametric Econometrics

Dr. Philip Shaw

Dealy Hall, East 522

Phone: 718-817-4048


Office Hours: Monday 3:30pm-5:00pm & Thursday 3:30pm-5:00pm in person or via zoom.

This course will cover nonparametric econometrics including univariate and multivariate density and conditional moment estimation.  A detailed discussion of bandwidth selection with mixed data will be covered with particular attention paid to interpretation of automatic dimension reduction.  We will also discuss the robust testing of significance, model specification, and density specification.  Finally, we address solutions to endogenity in the context of a generalized ill-posed inverse problem and introduce nonparametric panel data methods.  We will utilize R-software to both source and write scripts to implement the methods discussed throughout the semester.

The grading for the class breaks down as follows:

Midterm (40%)

Final Exam (40%)

Problem Sets (20%)


1. Racine, J.S. (2019),  An Introduction to the Advanced Theory and Practice of Nonparametric Econometrics (A Replicable Approach Using R), Cambridge University Press, ISBN 9781108483407, 408 pages

2. Li, Q. and J.S. Racine (2007), Nonparametric Econometrics: Theory and Practice, Princeton University Press, ISBN: 9780691121611, 746 Pages

Course Outline:

I. Probability Functions

1. Discrete Probability and Cumulative Probability Functions

2. Continuous Probability and Cumulative Probability Functions

3. Mixed-Data Probability Density and Cumulative Distribution Functions

4. Conditional Probability Density and Cumulative Distribution Functions

II. Conditional Moment Functions and Related Statistical Objects

5. Conditional Moment Functions

6. Conditional Mean Function Estimation

  • Local Constant Kernel Regression
  • Bandwidth Selection
  • Local Polynomial Kernel Regression
  • Fixed-effects Panel Data Models

7. Conditional Mean Function Estimation with Endogenous Predictors

  • Ill-posed Inverse Problems and Identification
  • Nonparametric Instrumental Variable Regression

Where to get R:

Simple Commands in R

R-code Posted Below

Problem Sets:


Data Sets and Descriptions:


Data Files in CSV Format



Additional Readings Posted Below