PREREQUISITES: This course assumes a knowledge of matrices, multivariate statistics and asymptotic theory. In addition knowledge of the multiple regression model, including model selection, hypothesis testing in large and small samples, multicollinearity, generalized least squares, heteroscedasticity, autocorrelation, instrumental variables, and nonlinear regression, and Bayesian methods is presumed. In this regard you may wish to review chapters 1 through 13 of Greene.
Computer: Familiarity with the statistical time series processor (TSP) on the VAX 8650 computer and/or microcomputer is also assumed. Use of these tools will be briefly reviewed in class. Manuals documenting the computer system, a TSP manual, and a simplified TSP manual are available for public use in BA 129, where computer terminals are also located. Computer manuals for personal use can be purchased in the bookstore.

OBJECTIVES: This course is intended to provide facility in the use and understanding of econometric techniques for rigorous analysis of economic models and data.

GRADING: Grades will be based on students' achievements relative to the class. Achievements will be judged on the basis of performance on examinations and homework according to the following weights:

                                    Midsemester Exam         40%
                                    Homework                     20%
                                    Final Exam                     40%
                                                                        100%

Assignments are expected to be submitted on their due date. However, unless otherwise stated, a late assignment will be accepted without penalty until the corrected assignments are returned and/or the answers to the assignment are distributed. While there will be no penalty on individual assignments for lateness, a penalty will be assessed if there is an excessive number of late papers.

Statement of Penalties and Procedures for Academic Dishonesty: The Graduate Bulletin contains a statement on standards of academic integrity, lists examples of academic dishonesty, and discusses penalties and procedures in cases of academic dishonesty. For this course the minimum penalty imposed on work tainted by academic dishonesty will be that the work will be assigned a grade of zero. Depending on the situation, a stronger penalty may be imposed. In addition, the Chair of the Department of Economics will be informed in writing of the incident and the penalty imposed. Further action may be taken at the Departmental and University levels.

I. The Seemingly Unrelated Regression and Multivariate Regression Models
     1. G, pp. 648-698.

II. Generalized Method of Moments
     1. G, pp. 517-535.
     2. Hansen, L., "Large Sample Properties of Generalized Method of Moments Estimators,"
         Econometrica,1982, 1029-1054.

III. Nonlinear Systems of Equations
     1. G, pp. 698-703

VI. Univariate Time Series
     1. G, pp. 823-850.

V. Lagged Variables
     1. G, Ch. 17
  * 2. Maddala, G. S., Econometrics, New York: McGraw-Hill, 1977, Ch. 15.
 

VI. Simultaneous Equations Models
     1. G., Ch. 16
  * 2. Maddala, Ch. 11; pp. 470-492.
  * 3. Greenberg, E., and C. Webster, Jr., Advanced Econometrics: A Bridge to the Literature,
         New York: Wiley, 1981, Chs. 2, 10.
  * 4. Klein, L., An Introduction to Econometrics, Englewood Cliffs, NJ: Prentice-Hall, 1962, Ch. 2.

VII. Multiple Time Series
     1. G, pp. 815-821, 851-870.

VIII. Panel Data Models
     1. G, Ch. 14.
     2. B, Ch. 1-7.

IX. Models with Discrete and Limited Dependent Variables
     1. G, Chs. 19, 20.

X. Resampling and Simulation Techniques: Monte Carlo, Bootstrap, Gibbs Sampler, Simulated Method of
    Moments
     1. Efron, B., and R. Tibshirani, An Introduction to the Bootstrap, New York: Chapman and & Hall,
         1993.
     2. Casella, G., and E. George, "Explaining the Gibbs Sampler," The American Statistician, 1992,
         167-174.
     3. Gelfand, A., and A. Smith, "Sampling Based Approaches to Calculating Marginal Densities,"
         Journal of the American Statistical Association, 1990, 972-985.
     4. Borsch-Supan, A., and V. Hajivassiliou, "Smooth Unbiased Multivariate Probability Simulators for
        Maximum Likelihood Estimation of Limited Dependent Variable Models," Journal of Econometrics,
        1993, 347-368.
 

OFFICE HOURS: TTh 2:00 PM - 3:00 PM and by appointment

Office: BA 110
Phone: 442-4744

* On Reserve in Library

 Kinal Home Page

Last Modified: 28 October 1997