AØKK08333U Seminar: Bayesian Econometrics

Volume 2015/2016
Education

MSc of Economics
The seminar is primary for students at the MSc of Economics

Content

This seminar will give a practical introduction to Bayesian inference in econometrics and train students to apply these methods empirically to economic models.

Bayesian methods offer a fresh perspective to econometrics, as they allow to tackle complicated estimation problems in an easy way. These approaches rely on simulation methods and can therefore have a clear advantage over classical methods. For instance, unobserved variables (like latent utilities or random effects) can be difficult to integrate out of a likelihood function, but are generally straightforward to simulate in a Bayesian framework.

Learning Outcome

At the end of the seminar, the students will be able to:

  • Understand Bayes' theorem and how it can be applied in econometrics.

  • Derive an algorithm to implement Bayesian methods for the inference of an economic model of their choice.

  • Develop a computer program or use an existing package publicly available to carry out their own empirical analysis.

Lynch, Scott M.  (2007). Introduction to Applied Bayesian Statistics and Estimation for Social Scientists. Springer. ISBN 978-0-387-71264-2.

 

Lancaster, Tony (2004). An Introduction to Modern Bayesian Econometrics. Blackwell Publishing. ISBN 978-1-405-11720-3.

 

Other references and scientific articles will be suggested to the students based on the subject they decide to study.

Since Bayesian econometrics stems from a different branch of statistics than frequentist approaches, this seminar will start from scratch and only requires students to be familiar with basic statistical principles (likelihood principle, conditional probabilities, density functions, etc.). However, a strong interest in econometrics and completion of the Econometrics A-B-C courses are highly recommended.

The course Advanced Microeconometrics is an advantage (but not a requirement) and can be taken in parallel with this seminar.

Bayesian econometrics relies on simulation methods. The seminar will therefore have a computational component. The R programming language will be introduced and used in this seminar. This particular programming language is not a pre-requisite (students will be allowed to use a different language like Matlab), but it is important that the students have some programming experience.
The seminar will be organized as follows:
• 3 introductory lectures manday 13-15 in week 37 to 39 and computer tutorials will be provided at the beginning of the semester to present the theoretical foundations of Bayesian methods and to get the students started.
• Students will have the freedom to choose one of the suggested topics or their own topic to write their term paper. The topic will be discussed and agreed with the teacher. Group work will be strongly encouraged.
• Supervision meetings will be organized with the teacher.
• Students will present their project during a workshop organized at the end of the semester (in week 47 or 48) and planned in collaboration with the students.
• Two additional weeks will be given after the workshop to finish the term paper and to incorporate the feedback obtained during the workshop.

Attendance of the introductory lectures and participation in the supervision meetings is compulsory to write a term paper and to participate in the workshop.

Workshop at the end of the semester:
• Paper draft and/or presentation slides should be handed in at least 2 days before the workshop.
• Oral presentation at workshop: 30 min. (20 min. presentation + 10 min. discussion).
• The term paper should be handed in two weeks after the workshop.



More information about seminars at
https:/​/​intranet.ku.dk/​economics_ma/​study_programme/​seminars/​Pages/​default.aspx
  • Category
  • Hours
  • Exam
  • 1
  • Project work
  • 185
  • Seminar
  • 20
  • Total
  • 206
Credit
7,5 ECTS
Type of assessment
Written assignment
Oral examination, 30 min under invigilation
A written seminar paper and a 20 minuts oral presentation for the others participans at the seminar and 10 minuts discussion.
Exam registration requirements

Attendance on the seminar. The mandatory commitment paper and seminar paper have been handed in at deadline.

Aid
All aids allowed
Marking scale
7-point grading scale
Censorship form
External censorship
up to 20 % censorship at the seminarpaper
Exam period

  • Paper draft and/or presentation slides should be handed in at least 2 days before the workshop.

  • Oral presentation at workshop: 30 min. (20 min. presentation + 10 min. discussion).

  • The term paper should be handed in two weeks after the workshop.

 

Re-exam

As ordinary.

Criteria for exam assesment

The student must in a satisfactory way demonstrate that he/she has mastered the learning outcome of the course.