ECON 400

B. Brown

Spring 2010






Our aim is to develop familiarity with a wide variety of linear statistical techniques which are routinely used in the analysis of economic data. Where appropriate, these techniques will be placed on a strong theoretical basis. Primary emphasis, however, will be placed upon applications using computer assignments and a critical analysis of the literature. As a byproduct, we hope to develop certain theoretical and computing skills that will facilitate the intelligent use of current techniques and mastery of additional techniques in the future.




Class meets thrice weekly for lectures.  Grades will be based 20% on (6 or so) problem sets, 10% on class participaton, 20% on each of two midterm examinations, and 30% on the final.




Familiarity with calculus, linear algebra, and mathematical statistics is expected.  Basic computer literacy will be needed to complete the problem sets.




The lectures will come primarily from my notes which will be made available in a timely fashion. The basic textbook for the course will be:


Verbeek, M., A Guide to Modern Econometrics, 2nd ed., Wiley, 2004.


This book should be available at the bookstore and the following alternative references should be on reserve at the library.


            Goldberger, A., Introductory Econometrics, Harvard, 1998.

Johnston, J. and J. Dinardo, Econometric Methods, 4th ed., McGraw-Hill, 1997.

            Schmidt, P., Econometrics, Marcel Deckker, 1976.


Computer Programs:


We will primarily use MATLAB for examples and problem sets.  MATLAB is a matrix programming language widely used in econometrics and all areas of science and engineering.  It should be available on all the lab PC's on campus and a student version for installation on your personal machine can be purchased for a nominal amount.  GAUSS is very similar to MATLAB, and is also widely used by economists.


Outline and Reading List:




1. Nature of Econometrics

2. Useful Distributions

3. Asymptotic Theory

            4. Maximum Likelihood Methods

            5. Matrix Algebra



                        *Notes, 1-5

                        *Verbeek, 1, 6, Appendices, A-B

                        Johnston and Dinardo, 1-2, 5, Appendices A-B

                        Goldberger, 1-5

                        Schmidt, Appendix



1. Bivariate Regression

            2. Multivariate Regression

            3. Statistical Results

            4. Hypothesis Testing

            5. Prediction



                        *Notes, 6-8

                        *Verbeek, 2-3

                        Johnston and Dinardo, 1-3

                        Goldberger, 6-12

                        Schmidt, 1



            1. Multicollinearity

            2. Stochastic Regressors

            3. Nonnormality

            4. Nonscalar Covariances

            5. Heteroskedasticity

            6. Serial Correlation

            7. Misspecification



                        *Notes, 9-14

                        *Verbeek, 4-5

                        Johnston and Dinardo, 4-6

                        Goldberger, 13-16

                        Schmidt, 2.1-2.5, 3.1-3.3



            1. Combining Non-Sample Information

            2. Nonlinear Regression

            3. Binary Variables

            4. Time-Series Models

            5. Panel Data Models



                        *Verbeek, 7-10                       

                        Johnston and Dinardo, 7-13

                        Goldberger, 17

                        Schmidt, 3.4



            1. Identification

            2. Limited Information Estimation

            3. Full Information Estimation

            4. Inference in SEM

            5. Prediction in SEM



                        *Verbeek, 5

                        Johnston and Dinardo, 9

                        Goldberger, 18-20

                        Schmidt, 4-5 


Disability Statement:


Any student with a documented disability needing academic adjustments or accommodations is requested to speak with me during the first two weeks of class. All discussions will remain confidential. Students with disabilities should also contact Disabled Student Services in the Ley Student Center .


Class Participation Policy:


The importance of class participation cannot be overemphasized. Having a class that is actively involved in the learning process is beneficial to all involved. Those who choose not to come to class and/or not to participate in the classroom activities are denying those involved in the class the positive externalities that would be generated by their involvement. The entire burden for making the interaction a success does not rest on the instructor since classroom learning is a two-way, highly interactive process. Since you signed up for a lecture class you should feel some obligation to attend the lectures in an active fashion. Class attendance is not mandatory but is highly recommended. In the past there has been a very high correlation between grades and attendance. It is possible to not come to class but read the book, do the homework, and take the exams and still obtain a decent grade. It will however be very difficult to obtain an A with this approach. There will be some material covered in-class that is not in the book and all assignments will be handed out in class and taken up in class (Do not e-mail me your assignments). Moreover, as stated above, a portion of the grade will be determined from an assessment of class participation. In structuring the grading in this fashion, we are just trying to reflect this portion of class performance that is so important to the success of the course to all involved.

Regrade Policy:


Feel free to ask for a regrade on any portion of a homework or exam that you feel has been mis-graded. Point totals that have been mis-added will be corrected with no questions asked. Beyond this, however, I reserve the right to regrade the entire exercise or exam if I feel that you are grubbing for points. In this case your grade is as likely to be lowered as raised. This is really just a question of fairness to the students that are not inclined to grub for points and reflects the fact that there is a certain amount of randomness in the grading process. In addition, I do not want to entertain arguments that I counted something similar to your answer correct on your friend's exercise or exam unless they are willing to submit their work for regrading as well. Again, this is just a question of fairness.