We cover:

- stationary multivariate time series models such as bivariate and multivariate vector autoregressions (VARs)
- volatility models such as GARCH and SV models
- if time allows: A short introduction to Bayesian econometrics

After this course, students are able to critically discuss empirical studies using the econometric methods covered in this course. Moreover, students can independently plan, conduct, interpret, and present their own data analyses.

100% physical, emotional, and intellectual participation is strongly recommended in all sessions. Absence in a maximum of two sessions will be tolerated. Note that there will be no chance to make up for any points which were lost due to missing any of the sessions, failing to hand in a case study on time, missing the midterm exam, or not attending the final presentations.

In-class, content is presented using the whiteboard and presentation slides. Moreover, the methods are illustrated via case studies using R and EViews. To ensure the in-depth applicability of the material presented, students will work in groups on extensive case studies and on a project. The solutions to the case studies must be handed in as written reports. The project will be presented in form of an oral presentation during the last two sessions.

The assessment is based on 3 components:

(1) Two case studies (10 points each, 20 points overall), accounts for 25% of the final grade
(2) Written exam in the antepenultimate session (30 points), accounts for 37.5% of the final grade
(3) Final presentation in the last two sessions (30 points), accounts for 37.5% of the final grade

The final grade will be determined as follows: 1 (at least 90%), 2 (at least 80%),  3 (at least 70%), 4 (at least 60%), 5 (less than 60%).

Successful completion of "Econometrics I" and "Econometrics II", i.e. an excellent conceptual and practical understanding of linear models and their statistical estimation (including common transformation of predictor and response variables, dummy coding of categorical predictors, models with trends and seasonalities, etc.), elementary time series econometrics (stationarity, common descriptive and inferential statistics for time series such as ACF, Durbin-Watson and Box-Ljung statistics, ARIMA models), and count / limited dependent variables models such as Poisson, negative binomial, logit, and probit regression. Working knowledge of R, EViews, or similar.