Hybrid teaching (alternating physical and online lectures).
|Montag||23.11.2020||09:00 - 12:00||Online-Einheit|
|Dienstag||24.11.2020||09:00 - 12:00||Online-Einheit|
|Montag||30.11.2020||09:00 - 12:00||Online-Einheit|
|Dienstag||01.12.2020||09:00 - 12:00||Online-Einheit|
|Montag||07.12.2020||09:00 - 12:00||Online-Einheit|
|Montag||14.12.2020||09:00 - 12:00||Online-Einheit|
|Dienstag||15.12.2020||09:00 - 12:00||Online-Einheit|
|Dienstag||12.01.2021||09:00 - 12:00||D2.0.330|
|Dienstag||19.01.2021||09:00 - 12:00||Online-Einheit|
This course offers a self-contained presentation of modern methods aimed at assessing specification uncertainty in econometrics, with a particular focus on applications to economic growth. The focus is on model averaging methods and, in particular, on Bayesian approaches to model uncertainty.
Students will be able to rigorously address model uncertainty in their inference using modern econometric methods.
Attendance is required throughout the course.
Frontal teaching in the first units, coupled with empirical exercises and group work, which will be presented by the students by the end of the course.
Assessment is based on class participation (10%), presentation of preliminary results of an empirical assessment (40%) and a paper to be handed in by the end of the course (50%).
Proficiency in econometrics (graduate level) is required. Knowledge in Bayesian statistics is an advantage, but not a necessity.