Updated A.Y. 2021-2022
Objectives: This course is designed to introduce students to econometric methods that are useful for the analysis of economic and financial time series. The objectives are to lay out the econometric theory of time series analysis and to analyze a data set methodically and comprehensively using econometrics tools.
Prerequisites: Familiarity with calculus, linear (matrix) algebra and basic mathematical statistics is expected. I shall also assume that students are familiar with the general linear regression model, its algebra, and estimation and inference within a framework.
Grading: Problem sets will account for 20% of the final grade. There will be a final exam that accounts for 80% of the final grade.
Textbooks and Notes: There will be a set of lecture slides and lecture notes that I will provide to you. You are expected to print and bring them to class. The recommended textbooks are:
Hamilton, J. D. (1994), "Time Series Analysis", Princeton University Press. Perron, P. (forthcoming). Advanced Econometrics. Boston University, USA.
Class schedule: Monday, Tuesday, Wednesday (9:00am-11:00am).
1. Difference Equations and Lag Operators.
2. Stationary Autoregressive Moving-Average (ARMA) models.
3. Maximum Likelihood Estimation of ARMA Models.
4. Wold's decomposition and Box-Jenkins modeling.
5. Long-run variance, HAC standard errors, robust inference.
6. Nonstationary stochastic processes (trends, structural change, unit roots and cointegration).
7. Vector Autoregression (VAR) models.
8. Structural Vector Autoregression (SVAR) models.