課程資訊

Econometrics (Ⅰ)

101-1

Fin8036

723ED6000

Ceiba 課程網頁
http://ceiba.ntu.edu.tw/1011metrics_fin

This is the first course in econometric theory for Ph.D. students; well prepared Master students are also welcome to take this course. This course requires knowledge of probability theory, multivariate statistics, and linear (matrix) algebra. Some econometrics knowledge at master level is a plus but not required. In this course, I will follow my own lecture notes and cover the least-squares theory and quasi-maximum likelihood theory. Unlike most econometrics textbooks that are organized according to models, my notes are arranged by theories (methods), with applications to various models. Some textbooks (R2 and R3 below) provide more thorough treatment of these topics. By introducing econometric theory in this way, I hope students will learn how an econometric method is derived and why it works. In addition, commonly used computational methods in econometrics, such as Monte Carlo simulation and bootstrap, will also be introduced.

The lectures will be in English; classroom discussion may be in Mandrin. To conduct simulations and bootstraps, students are required to learn at least one programming language, such as R (a free software) or Matlab. A senior student will introduce basic programming in R in the beginning lectures; some basic materials about R installation and introduction can be found in the class website (see below).

Course Outline

Part I: Classical Least Squares Theory (Chapters 3-4 of R1; S2; S4)
I.1 The Method of Ordinary Least Squares (OLS)
I.2 Properties of the OLS Estimator
I.3 Hypothesis Testing
I.4 Limitation of the Classical Conditions
I.5 The Method of Generalized Least Squares (GLS)

Part II: Asymptotic Least Squares Theory (Chapters 5-7 of R1; R2; R3)
II.1 Elements of Probability Theory
II.2 Asymptotic Properties of the OLS Estimator
II.3 Consistent Estimation of Asymptotic Covariance Matrix
II.4 Large Sample Tests
II.5 Digress: Bootstrap

Part III: Nonlinear Least Squares (NLS) Theory (Chapter 8 of R1; S1)
III.1 Nonlinear Speci cations
III.2 NLS Estimator

Part IV: Quasi-Maximum Likelihood (QML) Theory (Chapters 9-10 of R1; R3; S3)
IV.1 Kullback-Leibler Information Criterion
IV.2 Asymptotic Properties of the QML Estimator
IV.3 Information Matrix Equality
IV.4 Large Sample Tests - Nested Models
IV.5 Large Sample Tests - Non-Nested Models
IV.7 Applications: ARMA Models
IV.8 Applications: Volatility Models

Office Hours

S1. Davidson, R. and J. G. MacKinnon, Estimation and Inference in Econometrics, Oxford University Press, 1993.

S2. Greene, W. H., Econometric Analysis, 6th ed., Pearson Prentice Hall, 2008.

S3. Hamilton, J., Time Series Analysis, Princeton University Press, 1994.

S4. Kuan, C.-M., Elements of Matrix Algebra, Lecture Notes.

R1. Kuan, C.-M., Introduction to Econometric Theory, Slides and Notes, available at:
https://ceiba.ntu.edu.tw/1011metrics n (for nance students)
https://ceiba.ntu.edu.tw/1011metrics ib (for economics and IB students)
homepage.ntu.edu.tw/ckuan

R2. White, H., Asymptotic Theory for Econometricians, revised ed., Academic Press, 1999.

R3. White, H., Estimation, Inference and Speci cation Analysis, Cambridge University Press, 1994.

(僅供參考)

 No. 項目 百分比 說明 1. Midterm 45% 2. Final 40% 3. Homework 15%

 課程進度
 週次 日期 單元主題 第1週 9/10 1. Syllabus (2012.09.09 update); 2. R Installation Instructions (2012.09.09); 3. Getting started with R (2012.09.09) 第2週 9/17 Slide: Classical Least Squares Theory; Elements of Probability Theory; Asymptotic Least Squares Theory. Lecture: Ch1: Linear and Matrix Algebra, Ch2: Statistical Concepts, Ch3: Classical Least Squares Theory, Ch4: Generalized Least Squares Theory; Ch5: Elements of Probability Theory; Ch6: Asymptotic Least Squares Theory: Part I. R: lecture, code and homework 第3週 9/24 R: code and homework 第5週 10/08 Lecture: Ch8: Nonlinear Least Squares Theory, Ch9: Quasi-Maximum Likelihood Theory, Ch10: Quasi-Maximum Likelihood: Applications; Slide: Nonlinear Least Squares Theory, Quasi Maximum Likelihood Theory 第6週 10/15 Slide: Classical Least Squares Theory (2012.10.14 update); R: code & homework 第13週 12/03 Introduction to Time Series Analysis (2012.12.03) 第16週 12/24 Exam-ET_2010 (2012.12.24); Exam-ET_2011 (2012.12.24) 第17週 12/31 Introduction to Time Series Analysis (2012.12.30 update)