Course Director: Joann Jasiak Office hours: TBA Teaching Assistant: Maygol Bandehali , VH 1111, Mon 3-4, Wed: 10-11
This
is an intermediate course for students who have already taken an introductory
course(s) in econometrics or regression analysis. The objective is to introduce
students to the estimation and testing methods used in practice, and to provide
sufficient theoretical background for the extensions of the general linear
model. Those extensions will include the heteroscedasticity, error-in-variables
models, mulivariate linear models and their
estimators. Nonlinear models such as the Poisson, logit and probit
models, and the maximum likelihood estimator will also be covered. This course
will be focused on the analysis of cross-section data. All theoretical concepts will be
illustrated in class by empirical examples. Additional examples and problems
will be provided to students in assignments. Students will be allowed to work
in teams of two or (maximum) three. Suggested software are SAS, STATA and R.
Students who are not familiar with any of these can use SAS codes available
from this website. The prerequisites for this course are basic calculus,
mathematical statistics and matrix algebra. Detailed instructions on how to use
SAS on WEBFAS are provided on the ECON website. In order to access SAS go to:
https://webfas.yorku.ca/Citrix/WEBFASWeb/
Ajmani, V.B. "Applied Econometrics Using the SAS
System", Wiley 2009. Davidson, R., and J. MacKinnon
"Estimation and Inference in Econometrics", Oxford University Press,
1993
1. Review: General Linear Regression
Model and OLS (Greene 2,3) 2. Small sample properties of the
OLS (Greene 4) 3. Asymptotic theory and the
asymptotic properties of the OLS (Greene 4) 4. Maximum Likelihood (ML)
estimator-properties, examples: linear, binomial and Poisson models (Greene 16)
5. Restricted estimation, asymptotic
tests: Wald, LM, LR; (Greene 5) 6. Heteroscedasticity and Seemingly
Unrelated Regression (SUR) model (Greene 10) 7. Panel data, the Generalized Least
Squares (GLS) estimator (Greene 11) 8. Error-in-variable model, the Method of Moments (MM) and Instrumental
Variables (IV) estimators (Greene 12) 9. Simultaneous equations model and
the Two-Stage Least Squares (2SLS) estimator (Greene 13) 10. Probit
and Logit models for qualitative variables, ML (Greene 16) |