ECON 589 (Spring 2003)
Advanced Econometric Theory: Part I
Instructor: Prof. Herman J. Bierens (Tel.: 865-4921,
email: hbierens@psu.edu).
Office hours: Tuesday 2-4 PM
T.A.: None
Time: Monday and Wednesday 2-3:30 PM
Place: 413 Kern
Prerequisite level:
ECON 501 and ECON 510 (the sections for Ph.D. students
in economics), and ECON 511.
Required Texts:
-
[B] Bierens, Herman J. (1994): Topics in Advanced
Econometrics, Cambridge University Press (paperback version)
-
[D] Davidson, James (1994): Stochastic Limit Theory,
Oxford University Press
Objective
In the past few years the Department of Economics has
been trying to recruit junior econometricians for a position as Assistant
Professor, but without success. It appears that the supply of junior econometricians
by the top schools in the US has substantially fallen behind the demand.
Therefore, the Department of Economics at Penn State has decided to fill
this gap.
Of course, the main requirement for placement as
an econometrician at a research university is to write a econometrics thesis
of high quality, but for that you need to know much more econometrics than
you have had so far in ECON 501, 510 and 511. Consequently, this ECON 589
course, and its sequel in the Fall, is intended for Ph.D. students in economics
who want to specialize in econometrics.
The focus of this course is on asymptotic theory
and its applications in cross-section and time series econometrics.
The homework and exam arrangement will be decided
in January 2003.
Not all the topics are covered by the textbooks.
Additional literature will be provided during the semester.
Topics (tentative):
-
Review of asymptotic theory [B, Ch. 1-3; D, Ch.1-4,
7-11; lecture notes].
-
Cross-section data
-
Nonlinear regression analysis [B, Ch. 4, lecture notes]
-
Nonlinear method of moments [lecture notes]
-
Nonstandard maximum likelihood theory:
Mixed continuous-discrete distributions and censored
distributions, with applications to Tobit models, Heckman's sample selection
model, and censored duration models.
-
Time series data
-
Ergodicity, martingales and mixing conditions [B, Ch.
6; D, Ch. 13-19]
-
Laws of large numbers for dependent processes [B, Ch.
6; D, Ch. 20]
-
Uniform convergence [D, Ch. 21]
-
Central limit theorems for dependent processes [D, Ch.
24]
-
Nonlinear time series regression analysis
-
Nonlinear general method of moments for time series
models
-
Maximum likelihood theory for time series processes
-
Functional central limit theory [D., Ch. 26-30]
-
Approximation theory for functions: Fourier analysis,
Wavelets, and neural nets
Disability Message:
The Pennsylvania State University encourages qualified
persons with disabilities to participate in its programs and activities.
If you anticipate needing any type of accommodation in this course or have
questions about physical access, please tell the instructor as soon as
possible.