Event
Predictive Modeling [SS222521311]
Type
lecture (V)Präsenz/Online gemischt
Term
SS 2022SWS
2Language
EnglischAppointments
14Links
ILIASLecturers
Organisation
- KIT-Fakultät für Wirtschaftswissenschaften
Part of
- Brick Predictive Modeling | Industrial Engineering and Management (M.Sc.)
- Brick Predictive Modeling | Economics Engineering (M.Sc.)
- Brick Predictive Modeling | Information Systems (M.Sc.)
- Brick Predictive Modeling | Information Engineering and Management (M.Sc.)
- Brick Predictive Modeling | Economathematics (M.Sc.)
Literature
- Elliott, G., und A. Timmermann (Hrsg.): "Handbook of Economic Forecasting", vol. 2A und 2B, 2013.
- Gneiting, T., und M. Katzfuss: "Probabilistic Forecasting", Annual Review of Statistics and Its Application 1, 125-151, 2014.
- Hastie, T., Tibshirani, R., and J. Friedman: "The Elements of Statistical Learning", 2. Ausgabe, Springer, 2009.
- Weitere Literatur wird in der Vorlesung bekanntgegeben.
Appointments
- 20.04.2022 09:45 - 11:15 - Room: 11.40 Raum 221
- 27.04.2022 09:45 - 11:15 - Room: 11.40 Raum 221
- 04.05.2022 09:45 - 11:15 - Room: 11.40 Raum 221
- 11.05.2022 09:45 - 11:15 - Room: 11.40 Raum 221
- 18.05.2022 09:45 - 11:15 - Room: 11.40 Raum 221
- 25.05.2022 09:45 - 11:15 - Room: 11.40 Raum 221
- 01.06.2022 09:45 - 11:15 - Room: 11.40 Raum 221
- 15.06.2022 09:45 - 11:15 - Room: 11.40 Raum 221
- 22.06.2022 09:45 - 11:15 - Room: 11.40 Raum 221
- 29.06.2022 09:45 - 11:15 - Room: 11.40 Raum 221
- 06.07.2022 09:45 - 11:15 - Room: 11.40 Raum 221
- 13.07.2022 09:45 - 11:15 - Room: 11.40 Raum 221
- 20.07.2022 09:45 - 11:15 - Room: 11.40 Raum 221
- 27.07.2022 09:45 - 11:15 - Room: 11.40 Raum 221
Note
Contents
This course presents methods for making and evaluating statistical predictions based on data. We consider various types of predictions (mean, probability, quantile, and full distribution), all of which are practically relevant. In each case, we discuss selected modeling approaches and their implementation using R software. We consider various economic case studies. Furthermore, we present methods for absolute evaluation (assessing whether a given model is compatible with the data) and relative evaluation (comparing the predictive performance of alternative models).
Learning objectives
Students have a good conceptual understanding of statistical prediction methods. They are able to implement these methods using statistical software, and can assess which method is suitable in a given situation.
Prerequisites
Students should know econometrics on the level of the course `Applied Econometrics' [2520020]