The course focuses on econometric methods used in empirical applications with aggregate macroeconomic data. The course considers time series analysis from a Bayesian perspective and consists of the following main building blocks:

• (Recap: Mathematical tools, probability and statistics, classical econometrics)
• Univariate time series analysis
• Introduction to Bayesian econometrics
• Statistical software, algorithms and computation
• Multivariate time series analysis
• Structural identification, forecasting and predictive inference

We begin with briefly reviewing required mathematical concepts before proceeding with univariate time series methods such as autoregressive moving average (ARMA) models. Turning from theoretical considerations towards empirical implementations, we discuss Bayesian econometric methods for inference in a time series context. This also involves applied work with the statistical software R. Subsequently we generalize the preceding concepts to the multivariate case, and in particular will thoroughly discuss vector autoregressions (VARs). The topics we cover in this context include identification of structural shocks, and related tools such as impulse response functions. Finally, we will discuss forecasting and how to obtain statistical measures of predictive accuracy.

By the end of the course, students are expected to have acquired a good understanding of how to analyze univariate and multivariate time series, and how to apply this knowledge to macroeconomic data. This implies that they will be able to derive recommendations for policymakers from quantitative econometric models, and they can conduct their own research projects using time series analysis.

This course is designed for students interested in working at research or financial institutions, and covers the most important econometric tools used in empirical macroeconomics. Rather than focusing narrowly on the application of econometric tools in macroeconomics, the course aims to provide a deeper understanding of related methods, their proper use, and potential limitations. The methods discussed in the course, such as univariate and multivariate time series models, are used heavily in central banks and policy institutions. By the end of the course, students should be able to conduct their own small research projects using time series analysis.

Attendance is mandatory for this course, one absence will be tolerated.

Course materials will be made available to participants in the form of slides and computer code. The slides are partly based on the following books:

• Chan, J., Koop, G., Poirier, D.J. and Tobias, J.L.: "Bayesian Econometric Methods" (Cambridge University Press)
• Hamilton, J.D.: "Time Series Analysis" (Princeton University Press).

The lecture consists of two main blocks. First, we will discuss the topics listed in this syllabus based on the course materials (slides and codes) mentioned above. Second, you are asked to present seminal papers (which will be made available), in groups. The groups (max. 5 students) are expected to scrutinize the respective paper in depth (objectives, relevant assumptions, model framework, and results) and provide (1) a detailed discussion, as well as (2) potential comments/questions/suggestions. There will be sufficient time for thorough discussions in class. 

The relevant material for the exam is defined by what has been taught in the course.

The course grade will be based on the following components:

• Final exam (50 points)
• Paper presentation (30 points)
• Exercises (20 points)

To pass the course, a positive final exam score (50% or higher of total exam points) is required. The grading scheme is:

• Very good (1): [89, 100] points
• Good (2): [78, 89) points
• Satisfactory (3): [60, 78) points
• Sufficient (4): [50, 60) points
• Fail (5): [0, 50) points

The final exam will consist of a mix of multiple-choice and open questions, and will last for 60 minutes. It is scheduled to take place in our penultimate lecture.

Please log in with your WU account to use all functionalities of read!t. For off-campus access to our licensed electronic resources, remember to activate your VPN connection connection. In case you encounter any technical problems or have questions regarding read!t, please feel free to contact the library at readinglists@wu.ac.at.

michael.pfarrhofer@wu.ac.at