ECO644-01: Econometric Theory
Fall 2014
Instructor: Martijn van Hasselt
Office: Bryan 446
Phone: TBA
Email: mnvanhas@uncg.edu
Office hours: Tuesdays 10:00AM – 11:00AM, Thursdays 3:30PM – 4:30PM
Graduate Assistant: Maozhao Zheng
Email: m_zheng@uncg.edu
Office hours: TBA
Class times:
Location:
Tuesday, Thursday, 2:00PM – 3:15PM (lecture)
Tuesday, 12:30PM – 1:45PM (computer lab)
SOEB 219 (lecture [School of Education building])
Bryan 211 (computer lab)
Course description
This course provides an introduction to mathematical statistics and econometrics for students in
the Master’s program in economics. It emphasizes the theoretical underpinnings of econometrics
and is taught concurrently with ECO643 (which is a course in applied econometrics). Topics
include fundamental concepts of mathematical statistics (probability distributions, expected
value, hypothesis testing, sampling distributions, asymptotic analysis), linear algebra, and the
linear regression model. On completion of this course, students will have



a thorough understanding of some basic tools of mathematical statistics;
learned how these tools are used to analyze and understand the statistical properties of
linear econometric models;
applied these tools and techniques using SAS statistical software.
Course requirements
We will meet twice a week for a 75 minute lecture. The lectures are complemented by computer
labs, which are held on Tuesdays every 2-3 weeks. When a lab is scheduled, it replaces the
lecture on that day. The labs provide an introduction to the software (SAS, see below) and will
give you an opportunity to apply some of the material covered in the lectures.
Students are required to attend and actively participate in the lectures and labs. Cell phones must
be turned off. Laptops may be used for note taking but not for surfing the web or other
distracting activities. In addition to these responsibilities, students are expected to conform to the
University’s Student Code of Conduct (http://sa.uncg.edu/handbook/student-code-of-conduct/)
and to the Bryan School’s Faculty and Student Guidelines
(http://www.uncg.edu/bae/faculty_student_guidelines.pdf).
The grade for this course is based on the following components:



Problem sets: 20%
Midterm exam: 30%
Final exam: 50%
Problem sets will be given approximately every 2 weeks. They will receive a grade of 0, 1, or 2
(0 = no work or insufficient work; 1 = substantial work but many incorrect answers; 2 =
complete work with (mostly) correct answers). To receive credit, problem set answers need to be
turned in by the specified due date and time. Late answers will not be accepted without prior
approval of the instructor.
The problem sets will cover a combination of theory questions and computer assignments, based
on the material discussed in the labs. The midterm exam, scheduled for the week of October 7,
will cover all the material discussed up to that point. The final exam is cumulative and covers
material from the entire semester.
Software
The software package used in this course is SAS. SAS is installed in the UNCG computer labs.
SAS licenses for personal computers are available for UNCG students through ITS. To begin the
license process, connect to https://web.uncg.edu/research-access/secure/sas/sas.asp.
Academic Integrity
Students are expected to be familiar with and abide by the University’s Academic Integrity
Policy (see http://academicintegrity.uncg.edu/). Collaboration on problem sets and lab exercises
is allowed, but students must turn in their own work. Collaboration on exams is not allowed and
will be treated as a violation of the Academic Integrity Policy.
Course readings
We will use the following texts in this course (both are available at the campus bookstore).


Arthur S. Goldberger: A Course in Econometrics, Harvard University Press, 1991.
Rick Wicklin: Statistical Programming with SAS/IML Software, SAS Institute, 2010.
Course outline
Below is a list of topics and readings that will be covered during this course, together with a
tentative schedule. The schedule is subject to change, depending on whether extra time is
needed to cover certain topics. However, the exam dates are fixed and will not be moved.
Week
(1) Aug. 19, 21
(2) Aug. 26, 28
(3) Sep. 2, 4
Topics
Univariate probability and random
variables
 Discrete and continuous random
variables
 Probability mass function,
density, cumulative distribution
Expected values
 Mean and variance
 Univariate normal distribution
Lab: introduction to SAS IML
Bivariate distributions
 Joint, marginal and conditional
distribution
Readings
Goldberger, ch.2
Goldberger, ch. 3.1-3.4, 7.1
Goldberger, ch. 4, 5, 6, 7.27.4

(4) Sep. 9, 11
(5) Sep. 16, 18
(6) Sep. 23, 25
(7) Sep. 30, Oct. 2
(8) Oct. 7, 9
(9) Oct. 14, 16
(10) Oct. 21, 23
(11) Oct. 28, 30
(12) Nov. 4, 6
(13) Nov. 11, 13
Conditional expectations and
linear prediction
 Independence
 Bivariate normal distribution
Sampling distributions
 Random sampling
 Sample statistics (mean,
moments)
 Normal, student-t and chi-squared
sampling distributions
Lab: statistical functions and simulation
Asymptotic analysis
 Law of large numbers
 Central limit theorem
 Asymptotics of sample moments
Sampling distributions and asymptotic
analysis: the bivariate case
Lab: sampling distributions
Estimation
 Bias, efficiency, consistency
 Analogy principle, method of
moments, maximum likelihood
Matrix algebra: basic concepts
Midterm – October 7
Matrix algebra for least squares (LS)
estimation and random variables
Fall break: no class on October 14
The classical linear model
 Assumptions
 Properties of the LS estimator
 Gauss-Markov theorem
Lab: matrix calculations
The classical linear model
 Estimating linear functions of the
parameters
 Goodness-of-fit
 Short and long regression
The classical linear model
 Residual regression
Lab: matrix calculations in the linear
model
The normal linear model
 Multivariate normal distributions
 Maximum likelihood estimation
 Sampling distributions
Goldberger, ch. 8
Goldberger, ch. 9
Goldberger, ch. 10
Goldberger, ch. 11, 12.4, 13.113.2
TBD
Goldberger, ch. 14
Goldberger, ch. 15
Goldberger, ch. 16, 17.1-17.2
Goldberger, ch. 17.3-17.5
Goldberger, ch. 18, 19.1-19.4,
20.1-20.3,

Hypothesis testing and
confidence intervals
(14) Nov. 18, 20
The normal linear model (continued)
 Inference with unknown variance
 Hypothesis testing and
confidence intervals
Lab: multiple linear regression
(15) Nov 25, 27
Topics: TBD
Thanksgiving break: no class on
November 27
FINAL EXAM: December 6, 2014, 3:30PM – 6:30PM
Goldberger, ch. 21
TBD