Você está na página 1de 5

Berg Syllabus for ECO 6310, Fall 2008

Econometrics II
Section 001, call number 12613, meets TR 4:00 to 5:15pm in GR3.604

Instructor: Dr. Nathan Berg


Email: prof.berg@gmail.com
Phone: 972.883.2088
Office: Green Hall 2.804

Office Hours: By appointment. Please email me to schedule an appointment. If you’d like


to ask a question by email, that’s fine. If you’re asking for an appointment, I’d like you to
suggest a time (or several possible times) in your email.

Textbook
W.H. Greene, Econometric Analysis, 6th. ed., Upper Saddle River, NJ: Prentice-Hall, 2008.

Student Learning Objectives/Outcomes


This course promotes student learning in various ways.
• Understand the link between econometric analysis and economic theory
• Understand linear algebra and mathematical statistics that are the foundation for econometric
analysis
• Master basics of techniques to deal with panel and time-series data
• Know how to use and interpret standard techniques for models in which the dependent variable
is binary, discrete, or takes on values only on a restricted subset of the real line
• General knowledge of methodological approaches in econometrics (e.g., least squares,
maximum likelihood, general method of moments, non-parametric models, simulation and Monte
Carlo techniques)

Course & Instructor Policies


Absence from any exam must be properly documented; otherwise a grade of 0 is assigned to a
missed exam. Make-up exams are scheduled within the same week for those who missed an exam
with proper documentation. There is no extra credit work.

Grading
100 points can be earned during the semester from three primary sources:

(1) Homework (15 points)


(2) Test 1 (35 points) in-class, Thursday, Oct. 16
(3) Test 2 (50 points) 2pm, Thursday, Dec. 11

Final semester grades will be based on the following scale: 100 to 93 points earns an A;
A- for 92 to 90 points; B+ for 89-87 points; B for 86 to 83points; B- for 82 to 75 points;
C+ for 74 to 70 points; C for 69 to 65 points; C- for 64 to 60 points; D for 59 to 50
points; F for 49 or fewer points.
Course Plan
You should read Greene’s textbook in its entirety, Chapters 12-25. The subsections
that deserve extra attention when completing homework assignments and preparing for
exams are as follows:

Chapter 12 – Instrumental Variables Estimation


12.1 Introduction
12.2 Assumptions of the Model
12.3 Estimation
12.4 The Hausman and Wu Specification Tests and an Application to IV Estimation
12.9 Weak Instruments
12.10 Summary and Conclusions

Chapter 13 – Simultaneous Equations Models


13.1 Introduction
13.2 Fundamental Issues in SEMs
13.3 The Problem of Identification
13.5 Single Equation: Limited Information Estimation Methods
13.6 System Methods of Estimation
13.10 Summary and Conclusions

Chapter 14 – Estimation Frameworks in Econometrics


14.1 Introduction
14.2 Parametric Estimation and Inference
14.3 Semiparametric Estimation
14.4 Nonparametric Estimation
14.5 Properties of Estimators
14.6 Summary and Conclusions

Chapter 15 – Minimum Distance Estimation and the Generalized Method of


Moments (GMM)
15.1 Introduction
15.2 Consistent Estimation: The Method of Moments
15.3 Minimum Distance Estimation
15.4 The GMM Estimator
15.7 Summary and Conclusions

Chapter 16 – Maximum Likelihood Estimation


16.1 Introduction
16.2 The Likelihood Function and the Identification of the Parameters
16.3 Efficient Estimation: The Principle of Maximum Likelihood

2
16.4 Properties of MLEs
16.6 Hypothesis and Specification Tests and Fit Measures
16.7 Two-Step MLE
16.8 Psuedo-MLE and Robust Asymptotic Covariance Matrices
16.9 Applications of MLE
16.9.2 The Generalized Regression Model
16.9.3 Seemingly Unrelated Regression Models
16.9.5.b ML Estimation of a Geometric Regression Model for Count Data
16.9.6.a ML Estimation of the Linear Random Effects Model.
16.9.7.a A Finite Mixture Model
16.9.7.e Determining the Number of Classes
16.10 Summary and Conclusions

Chapter 17– Simulation-Based Estimation and Inference


17.1 Introduction
17.2 Random Number Generation
17.3 Monte Carlo Integration
17.4 Monte Carlo Studies
17.7 Summary and Conclusions

Chapter 18– Bayesian Estimation and Inference


18.1 Introduction
18.2 Bayes Theorem and the Posterior Density
18.3 Bayesian Analysis of the Classical Regression Model
18.4 Bayesian Inference

Chapter 19 – Serial Correlation


19.1 Introduction
19.2 The Analysis of Time-Series Data
19.3 Disturbance Processes
19.4 Some Asymptotic Results for Analyzing Time-Series Data
19.7 Testing for Autocorrelation
19.12 Forecasting in the Presence of Autocorrelation
19.13 Autoregressive Conditional Heteroscedasticity
19.13.1 The ARCH(1) Model

Chapter 20 – Model with Lagged Variables


20.1 Introduction
20.2 Dynamic Regression Models
20.5 Methodological Issues in the Analysis of Dynamic Models
20.6 Vector Autoregressions
20.7 Summary and Conclusions

Chapter 21 – Time-Series Models

3
21.1 Introduction
21.3 The Frequency Domain
21.4 Summary and Conclusions

Chapter 22 – Nonstationary Data


22.1 Introduction
22.2 Nonstationary Processes and Unit Roots (skim only)
22.5 Summary and Conclusions

Chapter 23 – Models for Discrete Choice


23.1 Introduction
23.2 Discrete Choice Models
23.3 Models for Binary Choice
23.4 Estimation and Inference in Binary Choice Models
23.4.1 Robust Covariance Matrix Estimation
23.4.2 Marginal Effects and Average Partial Effects
23.4.4 Specification Tests for Binary Choice Models
23.4.5 Measuring Goodness of FIT
23.5 Binary Choice Models for Panel Data
23.8 Bivariate Probit Models
23.9 A Multivariate Probit Model
23.10 Analysis of Ordered Choices
23.11 Models for Unordered Multiple Choices
23.12 Summary and Conclusions

Chapter 24 – Truncation, Censoring, and Sample Selection


24.1 Introduction
24.2 Truncation
24.3 Censored Data
24.3.1 The Censored Normal Distribution
24.3.2 Censored Regression (Tobit) Model
24.3.3 Estimation
24.5 Sample Selection
24.5.4 Regression Analysis of Treatment Effects
24.5.6 Estimating the Effect of Treatment on the Treated
24.5.8 Panel Data Application of Sample Selection Models
24.6 Summary and Conclusions

Chapter 25 – Models for Event Counts and Duration


25.1 Introduction
25.2 Models for Counts of Events
25.3 Panel Data Models
25.6 Models for Duration Data
25.7 Summary and Conclusions

4
Schedule Problems
If you have an emergency or a valid conflict and provide me with written documentation,
I will consider granting an extension or providing an alternative assignment. Otherwise, I
do not want to extend any deadlines or permit schedule changes. Late papers will be
penalized up to 10 percentage points per day. Papers that are several days late may not be
accepted at all. I want you to succeed in this class. Please stay organized and work well
ahead of deadline.

Incompletes
There will be no grades of incomplete awarded without appropriate documentation.

Scholastic Dishonesty
Scholastic dishonesty includes, but is not limited to, cheating on assignments or
examinations, plagiarizing (misrepresenting as your own work any part of work done by
another), submitting the same assignment, or substantially similar assignments to meet
the requirements of more than one course without the approval of all instructors,
depriving another student of necessary course materials, or interfering with another
student's work. If in doubt about the ethics of your actions, consult the Catalog to see the
University's policy. Scholastic dishonesty will not be tolerated. Students are responsible
for knowing what constitutes scholastic dishonesty and its consequences (see
http://www.utdallas.edu/student/slife/chapter49.html). If you have any doubts, contact me
before you turn in your assignments.

Accessibility (for students with disabilities)


If you have a condition that requires accommodation in this course, please speak with me
after class or in office hours during the first week of class. I will be happy to make
appropriate accommodations provided timely notice is received and the arrangement is
consistent with any recommendations from Disability Services, when applicable.
Disability Services can be reached at 883-2098. The syllabus and other course materials
can be made available in alternative formats.

Attendance Policy
There is no explicit attendance requirement for this course. However, if students expect
to do well, regular attendance is necessary. Assignments may change, and adjustments to
the exam schedule may occur. Students who miss deadlines or fail to complete an
assignment because they did not hear scheduling announcements in class will not be
excused. Please do not ask me for notes.

Disclaimer:
This syllabus is tentative and can be changed. All changes will be announced in class.

Você também pode gostar