Applied Advanced Econometrics
Course Syllabus
Fall 2016, TTH 6:40-8:30pm (CH-307)
Prof. K.-P. Lin (CH-241G, 725-3931)
Office Hours: TTH 3:30-4:30pm or by Appointment
(Last updated: 11/10/2016)
This course covers advanced topics related to methodological issues in
econometrics, with emphases on computation intensive methods and applications.
We assumes background knowledge of linear econometric models,
and study the nonlinear models and optimization techniques.
The purpose of this course is to prepare students with a broad
coverage of econometric methods and applications capable of doing
independent research project. In addition to economic theory, knowledge
of mathematics, statistics, and basic econometrics is required. Experience of computer
programming is helpful but not necessary. Software R is used throughout the course.
Texts
- W. H. Greene,
Econometric Analysis, 7th ed., Pearson Education, 2012.
- J. M. Wooldridge,
Econometric Analysis of Cross Section and Panel Data, 2nd ed., The MIP Press, 2010 (Recommended).
- A. Colin Cameron and Pravin K. Trivedi,
Microecometrics: Methods and Applications, Cambridge University Press, 2005 (Recommended).
Software
Course Topics
Lecture notes will be updated and available online for download during class in progress.
Econometric Computing with R
- Matrix Algebra in R
- R Programming
Nonlinear Optimization
- Unconstrained Optimization
- Constrained Optimization
Classical Nonlinear Regression Models
- Nonlinear Least Squares (NLSQ)
- Maximum Log-Likelihood (ML)
- M-Estimation
- Statistical Inferences in Nonlinear Models
- Applications
Generalized Linear Models
- Binary Choice Models: Probit, Logit
- Count Data and Posisson Model
Generalized Method of Moments
- Nonlinear Generalized Method of Moments (GMM)
- GMM Estimation for Econometric Models
- Application: A Nonlinear Rational Expectation Model
Course Expectation
This course consists of lectures, readings, homework, presentation, and final exam.
Each student is expected to present the assigned readings on a specific topic.
In addition, there are 4-5 homeworks (once every two weeks in average).
Doing homework is very important not only to understand the theoretical
concepts but also to learn structural and efficient computing techniques
for econometric estimation and inference. The time schedule and grade distribution are as
follows:
- Homework (30%): Due every 2 weeks
- Homework 1
- Homework 2
- Homework 3
- Homework 4
- Presentation(30%):
Topics are based on the chapters of the following readings
- J. Angrist and J.-S. Pischke,
Mastering 'Metrics: The Path from Cause to Effect, Princeton: Princeton University Press, 2014.
- J. Angrist and J.-S. Pischke,
Mostly Harmless Econometrics: An Empiricist's Companion, Princeton: Princeton University Press, 2009.
- H. R. Varian,
Causal inference in economics and marketing, PNAS (July 5, 2016), vol. 113 no. 27, 7310-7315.
- Regression: A Review
- Instrumental Variables
- Regression Discontinuity
- Difference in Difference
- Quantile Regression
- Nonstandarded Standard Error Issues
- Final Exam (40%)