5457 Y2E Advanced Topics in Financial Econometrics
Mag.Mag.Mag.Dr. Gregor Kastner
Contact details
Weekly hours
Language of instruction
02/07/19 to 02/24/19
Registration via LPIS
Notes to the course
Day Date Time Room
Wednesday 03/06/19 03:00 PM - 07:00 PM D4.0.127
Wednesday 03/13/19 03:00 PM - 07:00 PM D4.0.127
Wednesday 03/20/19 03:00 PM - 07:00 PM D4.0.127
Wednesday 03/27/19 03:00 PM - 07:00 PM D4.0.127
Wednesday 04/03/19 03:00 PM - 07:00 PM D4.0.127
Wednesday 04/10/19 03:00 PM - 07:00 PM D4.0.127
Wednesday 05/08/19 03:00 PM - 07:00 PM D4.0.127
Wednesday 05/15/19 03:00 PM - 06:30 PM TC.4.01
The course starts with a concise coverage of elementary concepts and computational tools for Bayesian modeling of financial data. Furthermore, it aims at complementing students' econometric comptetence in data analysis with a focus on Bayesian approaches. Towards the end of this course, state-of-the art univariate and multivariate volatility models are discussed and applied to real world data. Focus will be placed on topics that are of particular interest to the participants.
Learning outcomes

After completing this class the student will have the ability to:

  • fundamentally understand concepts, techniques and tools in Bayesian data analysis
  • know about various computational approaches towards Bayesian econometrics
  • use hierarchical models to answer economic questions
  • apply univariate and multivariate models for capturing heteroskedasticity in (financial) time series
  • independently and competently perform Bayesian analysis of economic time series
  • compare different approaches to point- and density-prediction
  • evaluate various forecasting techniques
  • connect to state-of-the art literature in Bayesian modeling of economic and financial data
Attendance requirements

For this lecture participation is obligatory. Students are allowed to miss a maximum of 20% (no matter if excused or not excused).

Teaching/learning method(s)
The course consists of a mix between lectures and tutorials, reading assignments, case studies and students' presentations. Participants are required to independently apply the models to actual data problems, both in-class as well as between-classes.

The grade is composed as follows:

05 points: active classroom participation
15 points: students' presentations
40 points: case studies / homework
40 points: final exam

Overall, 100 points can be achieved. The final grade is computed according to

min(5, (110-x)/10), rounded towards the better grade,

where x is the number of points achieved.

1 Author: Hoff, Peter D.

A First Course in Bayesian Statistical Methods

2 Author: Koop, Gary
Title: Bayesian Econometrics

3 Author: Blake, Andrew & Mumtaz Haroon
Title: Applied Bayesian econometrics for central bankers

Recommended previous knowledge and skills
A solid understanding of “classical” (financial) econometrics. Good programming skills in a high-level language such as R.
Last edited: 2019-01-10