Syllabus for ECN/EEC676, Advanced Econometrics

Syllabus for ECN/EEC676, Advanced Econometrics
Spring 2014
John P. Burkett
Introduction: This course covers econometric foundations and selected
applications. After briefly reviewing parts of probability and introductory
econometrics, we shall focus on the maximum likelihood, generalized method
of moments, and Bayesian approaches and their application to forecasting,
systems of regressions, simultaneous equations, and discrete choice models.
We will aim to achieve a command of econometric theory and computer
programming sufficient for solving novel problems with more flexibility than
allowed by the limited menus of traditional econometric software packages.
Readings: The texts are Ron C. Mittelhammer et al., Econometric Foundations (Cambridge: Cambridge University Press, 2000); Edward Greenberg,
Introduction to Bayesian Econometrics, second edition (Cambridge: Cambridge University Press, 2013); and Christian Kleiber and Achim Zeileis,
Applied Econometrics with R (New York: Springer, 2008). In the calendar
below, readings from Greenberg, Kleiber & Zeileis, and Mittelhammer et al.
are denoted by Gx, Kx, and Mx, where x is a chapter, appendix, section,
or page number or range. The chapters reviewing familiar material may
skimmed. Those covering new material should be read carefully. Supplemental readings (including those listed in the calendar as Diebold, Geweke,
Rossi, and Stock) will be available as handouts or at the Library’s reserves
desk.
Web page: Computer code and other items useful to econometricians are
available at http://www.uri.edu/artsci/ecn/burkett/676s14.htm. This site
will be updated from time to time during the semester.
Evaluation: Your course grade will depend on a midterm exam (25%), a
forecasting project (20%), class participation (15%), and a final exam (40%).
Forecasting project: You will be asked to forecast the Bureau of Economic Analysis’s advanced estimate of the growth rate for U.S. Gross Domestic Product for the first quarter of 2014. Your grade in this assignment
will depend equally on the accuracy of your forecast and the quality of the
econometric reasoning underlying it.
Contact information: I can be reached at 874-9195 or [email protected].
My office hours are Tuesday and Thursday, 9:30–10:30 a.m. or by appointment in 215 Coastal Institute.
1
Calendar
Date
Jan. 23
Jan. 28
Jan. 30
Feb. 4
Feb. 6
Feb. 11
Feb. 13
Feb. 18
Feb. 20
Feb. 25
Feb. 27
Mar. 4
Mar. 6
Mar. 18
Mar. 20
Mar. 25
Mar. 27
Apr. 1
Apr. 3
Apr. 8
Apr. 10
Apr. 15
Apr. 17
Apr. 22
Apr. 24
Apr. 29
Topic or Event
Probability review
Introduction to R
Econometric models & programs
Exercises
Maximum likelihood estimation
Maximum likelihood inference
Stochastic regressors & method of moments
Exercises
Generalized method of moments
Time series
Forecasting
Exercises
Midterm exam
Bayesian theory
Bayesian regression
Bayesian computation
Exercises
Bayesian GMM, time series, & forecasting
Systems of equations
Simultaneous equations
Exercises
Basic discrete choice models
Discrete choice models in R
Bayesian logit & probit
Exercises
Presentation of forecasts
2
Readings
G2.1
K1, 7.4
M1–2; K2
M3; K3.1–3.4
M4; K pp. 63–65, 68–69, K4.1–4.3
M10
M16.1–16.4.2
Diebold pp. 315–26; K3.5, 6
Stock pp. 562–84
M22.1–2; G 2.2–4.11
M22.3–22.7, 23.1–23.3, 24
MA.4; G5–8.1
G11; Geweke pp. 6–24, 53–60
M15.2; K3.6–3.7; G10
M17.1–17.4; G12.1–12.2
M20.1–20.3
K5.1–5.3
G8.2.2–8.2.3; Rossi 4