The aim of the course is to introduce students to applied econometrics analysis that deal specifically with macroeconometric models. The focus of the course will be on time series methods. The course serves as a solid background to study specific topics within macroeconometrics at the same time that it provides econometric tools that can be readily applied to time series data.
Joao B. Duarte
Weekly - Available soon
Total - Available soon
The main material will be handouts given in class. Macroeconometrics still lacks a unified textbook. Seminal papers with an application of a specific topic will be advertised during lectures. Additionaly, students are adivised to better understand a particular topic in the following textbooks:
Enders, W. (2014), Applied Econometric Time Series, 4th ed., John Wiley & Sons, Inc.
Hamilton, J.D. (1994), Time Series Analysis, Princeton University Press.
Canova, F. (2007), Methods for Applied Macroeconomic Research, Princeton University Press.
Introduction to R: https://cran.r-project.org/doc/manuals/r-release/R- intro.pdf
R time series packages: https://cran.r-project.org/web/views/TimeSeries.html
Students should attend weekly classes to understand and learn to use the main time series macroeconometric tools and the theoretical arguments used to derive the main results, and to get acquainted with the interpretation of the results for selected empirical examples. Students are expected to participate actively in the discussions of the examples covered in class. Reading of the required texts is essential since they provide detailed discussions of each topic and provide students with several additional examples illustrating the applicability of the general techniques. Computer lab sessions will help students to use specialized econometric software tools. Group and individual assignments are important to develop all the learning objectives. This is an applied empirical class, hence the learning success hinges on active participation of the students.
The final course grade is based on a midterm exam (30%), a final exam (40%), one individual assignment (10%), and two group assignments (20%). Groups will be pre- defined by the Master's Office. Grades for the assignments will specifically take into account the quality of the work done and the autonomy of the group. All important assessment dates will be posted at the course page on moodle.
First problem set – Due February, 28th
Second problem set – March, 14th
Midterm exam – March, 21st
Thid problem set – May, 2nd
Final exam – May, 22nd
1. Basic concepts in time-series analysis:
Stationarity and ARMA models;
2. VAR models:
Structural VAR with recursive identification;
Alternative identification methods.
3. Modeling trends and cycles:
HP and band-pass filters;
Unit-roots and cointegration;
4. Bayesian Analysis:
5. Models for unobserved components:
State space models;
The Kalman filter;
6. Modeling volatility:
Univariate and multivariate ARCH-type models.
7. Non-linear models:
TVAR and STVAR models;
Markov-switching state space models.