Sie sind auf Seite 1von 5

ECO 341K -- 33677

University of Texas at Austin

Prof. Richard Chiburis


Spring 2010

Syllabus: ECO 341K (Introduction to Econometrics)


Tuesdays/Thursdays 12:30-1:45, ART 1.110

Instructor

Teaching Assistant

Prof. Richard Chiburis


E-mail: chiburis@austin.utexas.edu
Office: BRB 3.160
Office hours: Mon. 9-10am, Wed. 4-5pm

Hao Han
E-mail: haohan@mail.utexas.edu
Office: BRB 2.128
Office hours: Mon. & Fri. 1-2pm

Objectives
The goal of this course is to provide students with the knowledge and tools to conduct their
own empirical research in economics, to evaluate government and business policies, to perform
forecasting, and to critically read statistical analyses by researchers and in the media. Students
will learn to use the computer as a tool for regression analysis, but more importantly we will
focus on the proper interpretation of the underlying statistical models so that students
understand when particular methods are likely to be valid (or invalid!).

Textbook
The required textbook for this course is Introductory Econometrics: A Modern Approach, 4th
edition, by Jeffrey Wooldridge. Although we will jump around in the book throughout the
course, we will follow the content in the book rather closely. The 3rd edition is also fine (and
probably a lot cheaper if you can find it used).

Prerequisites
Economics 420K (Microeconomic Theory) and 329 (Economic Statistics) with a grade of at least
C in each. You should be familiar with most, if not all, of the material in Appendices A (Basic
Mathematical Tools), B (Fundamentals of Probability), and C (Fundamentals of
Mathematical Statistics) of the textbook.

STATA Software
Real-world examples and actual data analysis are an essential part of this course! We will use
the statistical package STATA. It is very easy to learn. Class examples will be illustrated using
STATA, and students will be expected to use STATA for the empirical exercises on their problem
sets. There are a few options for accessing STATA: (i) (recommended) establish an Austin Disk
Services account (if you havent already) for a small annual fee ($5) and use STATA on Windows
Terminal Services (I have prepared a separate handout on how to do this) , (ii) use the
computers in the BUR 120 or 124 labs, or (iii) purchase your own one-year license ($98) for

STATA/IC 11 (not Small STATA) through http://www.stata.com/order/new/edu/gradplans/gpdirect.html.

Website (Blackboard)
All lecture notes, example sheets, homework assignments/solutions, and STATA datasets will be
posted on the course Blackboard site.

Grading
Your course grade will be broken down as follows:
Homework:
20%
Two in-class exams: 20% each (February 23 and April 8)
Final exam:
40% (Wednesday, May 12, 2-5pm)
Extra Credit:
2.5%
I will use the plus/minus grading system. I do not take attendance.

Homework
There will be weekly assignments due at the beginning of Tuesdays classes (approximately 10
assignments total). Late assignments will not be graded. If you cannot make it to class, have a
classmate bring your assignment or e-mail it to me before class begins. You may work with one
other person on the homework, but you must turn in your own answers (and indicate with
whom you worked). Include all necessary computer output with your assignment.
Assignments will be graded on a + / / - system. In computing your total homework grade,
I will use the following point system:
+
5 points

4 points
3 points
Not turned in: 0 points
You will be allowed to drop your two lowest scores on the assignments.

Extra Credit
Be on the lookout for misuses of statistics in the news, especially the mistaking of correlation
for causality. Email me such an article along with your own interpretation, or bring it up in
class, and I will give you some extra credit (2.5%) on your course grade.

Exams
All exams will be closed book. I will provide a common formula sheet with the exams to
minimize the amount of memorization required. There will be no make-up exams for the inclass exams; if you have a valid medical excuse (and a doctors note), I will put more weight on
the final.

University Notices
University of Texas Honor Code
The core values of The University of Texas at Austin are learning, discovery, freedom,
leadership, individual opportunity, and responsibility. Each member of the university is
expected to uphold these values through integrity, honesty, trust, fairness, and respect toward
peers and community.
Documented Disability Statement
The University of Texas at Austin provides upon request appropriate academic
accommodations for qualified students with disabilities. For more information, contact
Services for Students with Disabilities at (512) 471-6259 (voice) or 1-866-329-3986 (video
phone).

Course outline (topics near end to be covered as time permits; W= Wooldridge chapters):
1. Introduction (W 1)
a. What is econometrics?
b. Types of economic data
c. Causality vs. correlation
2. The simple regression model (W 2.1-2.5)
a. Model and assumptions
b. Ordinary least squares (OLS) estimator
c. Goodness-of-fit and R-squared
d. Non-linear (logarithmic) transformations
e. Properties of OLS
3. The multiple regression model (W 3)
a. How do the simple regression results extend?
b. Omitted variables bias
c. Multicollinearity
d. Gauss-Markov theorem: efficiency of OLS
4. Statistical inference for OLS (W 4, 5)
a. Single-parameter tests: t-test
b. Two-sided versus one-sided test
c. p-values
d. Confidence intervals
e. Multiple restriction tests: F-test
f. Asymptotic (large sample) theory for OLS (W 5.1-5.2, skip the LM statistic in
5.2)
5. Additional issues in regression analysis
a. Selection of regressors (6.3)
b. Prediction (6.4)
c. Binary variables, Policy evaluation (7)
d. Heteroskedasticity (W 8.1-8.3, skip LM test in 8.2, skip White test in 8.3)
e. Measurement error (W 9.4)
f. Missing data/Sample selection (W 9.5, skip Outliers)
6. Time series (W 10, 11, 12 (skip 12.3, 12.6), 18 (skip 18.1, 18.4))
a. Trends and seasonality
b. Serial correlation --- AR(1) model, random walk
c. Forecasting
7. Panel data (W 13, 14.1, 14.3)
a. Pooled cross sections
b. Fixed effects model
8. Binary-choice models (W 17.1)

9. Instrumental variables (W 15.1-15.3)


a. Endogeneity
b. Two-stage least squares estimation

Date
Tu Jan. 19
Th Jan. 21
Tu Jan. 26
Th Jan. 28
Tu Feb. 2
Th Feb. 4
Tu Feb. 9
Th Feb. 11
Tu Feb. 16
Th Feb. 18
Tu Feb. 23
Th Feb. 25
Tu Mar. 2
Th Mar. 4
Tu Mar. 9
Th Mar. 11
Tu Mar. 23
Th Mar. 25
Tu Mar. 30
Th Apr. 1
Tu Apr. 6
Th Apr. 8
Tu. Apr. 13
Th Apr. 15
Tu Apr. 20
Th Apr. 22
Tu Apr. 27
Th Apr. 29
Tu May 4
Th May 6
W May 12

Class Schedule
Wooldridge Chapters Class Topic
1
Introduction -- Syllabus
1
Data, Models, Correlation-Causality
2
SLRM Assumptions, OLS
2
SLRM -- Interpretation, Transformation, Fit
2
SLRM -- Properties of OLS
3
MLRM -- Model, Assumptions, OLS
3
MLRM -- Interpretation, Fit
3
MLRM -- Exp. Value, Omit. Var., Collin.
3
MLRM -- Variance, Gauss-Markov Thm.
Review Session
MIDTERM EXAM 1
7.6
Policy Analysis and Program Evaluation
4
Inference -- Small Sample
4
Inference -- Small Sample
5
Inference -- Large Sample
6.2-6.4
Quadratics, Regressor selection, Prediction
SPRING BREAK
7.1-7.4
Further Issues -- Dummies, Interactions
7.5, 17.1
Binary Choice
8.1-8.3
Heteroskedasticity
9.4-9.5
Measurement error, Missing data (sample selection)
Review Session
MIDTERM EXAM 2
10
Time Series Regression
11
Time Series Regression
12.1-12.2, 12.4-12.5 Time Series: Serial Correlation of error terms
18.2, 18.3, 18.5
Time Series: Random walks, Forecasting
13
Pooled Cross Section
14
Panel Data Regression (Fixed Effects)
15
Instrumental Variables (IV)
Review Session
FINAL EXAM 2-5pm

Assignments

HW1 Due
HW2 Due
HW3 Due
HW4 Due

HW5 Due

HW6 Due
HW7 Due

HW8 Due
HW9 Due
HW10 Due
Extra Credit Due