Zur Merkliste hinzufügen


30661-01 - Vorlesung: Advanced Time Series Analysis 3 KP

Semester Frühjahrsemester 2023
Angebotsmuster Jedes Frühjahrsem.
Dozierende Simon Beyeler (simon.beyeler@unibas.ch)
Sylvia Kaufmann (sylvia.kaufmann@unibas.ch, BeurteilerIn)
Inhalt The course introduces modern multivariate time series modelling, in particular vector autoregression with hierarchical extensions and applications in macroeconomics.

In a first part, we discuss a vector autoregression from an analytical viewpoint. We derive properties of the time series process, discuss stationarity and invertibility conditions, derive conditional and unconditional moments. As single parameters are not of prime interest, tools like impulse responses and variance decomposition are used to interpret multivariate time series models. Besides improving structural in-sample analysis, multivariate models eventually improve forecasting performance.

We briefly review model estimation from a frequentist perspective, as a basis to introduce the Bayesian approach. A Bayesian approach circumvents estimation difficulties when either data is scarce or high-dimensional. We introduce two basic samplers based on Markov chain Monte Carlo (MCMC) simulation methods to obtain posterior inference: Gibbs and Metropolis-Hastings sampling. To quantify uncertainty, we derive procedures to obtain confidence or credible intervals. Finally, we discuss approaches to perform model choice or (forecast) evaluation, like MCMC-based estimation of the marginal likelihood or K-fold cross-validation.

The last part introduces latent variables into multivariate modelling. These capture latent processes determining observed data like regime-switching parameters or underlying common factors.

The lecture includes exercise sessions with applications in macroeconomics.
Lernziele - Analyse and derive the properties of multivariate time series models.
- Perform model specification/comparison; understand and apply tools to interpret model estimates.
- Understand the differences between frequentist estimation and Bayesian inference.
- Implement estimation and various structural identification procedures, quantify uncertainty.
- Estimate basic latent variable models.
- Basic knowledge of forecasting procedures, forecast evaluation.
Literatur Gelman A., Carlin J.B., Stern H.S. and Rubin, D.R. (1995), Bayesian Data Analysis, Chapman and Hall, London.
Greenberg Edward, 2013, Introduction to Bayesian Econometrics, Cambridge University Press, Cambridge UK.
Lütkepohl Helmut, 2005, New Introduction to Multiple Time Series Analysis, Springer.
Neusser Klaus, 2016, Time Series Econometrics, Springer International Publishing AG Switzerland.

Popular scientific:
Bertsch Mcgrayne Sharon (2011), The theory that would not die: how bayes' rule cracked the enigma code, hunted down russian submarines, and emerged from two centuries of controversy, Yale University Press, New Haven & London..
Bemerkungen The course will be taught onsite.
Weblink Weblink


Teilnahmebedingungen Completed BA (preferably in economics).
Econometrics MA level: Knowledge in regression analysis, univariate time series analysis (advantageous).

Knowledge in econometrics or programming software (like e.g. EViews, matlab, R)
Anmeldung zur Lehrveranstaltung Registration: Please enrol in MOnA. EUCOR-Students and students of other Swiss Universities have to enrol at the students administration office (studseksupport1@unibas.ch) within the official enrolment period. Enrolment = Registration for the exam!
Unterrichtssprache Englisch
Einsatz digitaler Medien kein spezifischer Einsatz


Intervall 14-täglich
Datum 22.02.2023 – 31.05.2023
Zeit Mittwoch, 14.15-17.45 Wirtschaftswissenschaftliche Fakultät, Seminarraum S15 HG.31
Datum Zeit Raum
Mittwoch 22.02.2023 14.15-17.45 Uhr Wirtschaftswissenschaftliche Fakultät, Seminarraum S15 HG.31
Mittwoch 08.03.2023 14.15-17.45 Uhr Wirtschaftswissenschaftliche Fakultät, Seminarraum S15 HG.31
Mittwoch 22.03.2023 14.15-17.45 Uhr Wirtschaftswissenschaftliche Fakultät, Seminarraum S15 HG.31
Mittwoch 05.04.2023 14.15-17.45 Uhr Wirtschaftswissenschaftliche Fakultät, Seminarraum S15 HG.31
Mittwoch 19.04.2023 14.15-17.45 Uhr Wirtschaftswissenschaftliche Fakultät, Seminarraum S15 HG.31
Mittwoch 03.05.2023 14.15-17.45 Uhr Wirtschaftswissenschaftliche Fakultät, Seminarraum S15 HG.31
Mittwoch 17.05.2023 14.15-17.45 Uhr Wirtschaftswissenschaftliche Fakultät, Seminarraum S15 HG.31
Mittwoch 31.05.2023 14.15-17.45 Uhr Wirtschaftswissenschaftliche Fakultät, Seminarraum S15 HG.31
Module Modul: Fachlich-methodische Weiterbildung (Doktoratsstudium - Wirtschaftswissenschaftliche Fakultät)
Modul: Field Electives in Economics and Public Policy (Masterstudium: Economics and Public Policy)
Modul: Field Electives in Finance and Money (Masterstudium: Finance and Money)
Modul: Finance Field: Monetary Economics and Macrofinance (Masterstudium: Finance and Money)
Modul: Specific Electives in Data Science and Computational Economics (Masterstudium: Wirtschaftswissenschaften)
Modul: Specific Electives in Economics (Masterstudium: Wirtschaftswissenschaften)
Modul: Statistik und Computational Science (Masterstudium: Actuarial Science)
Spezialisierungsmodul: Areas of Specialization in International and/or Monetary Economics (Masterstudium: International and Monetary Economics)
Vertiefungsmodul: Quantitative Methods (Masterstudium: Wirtschaftswissenschaften (Studienbeginn vor 01.08.2021))
Leistungsüberprüfung Leistungsnachweis
Hinweise zur Leistungsüberprüfung 40% Two assignments (team work of 3-5 persons)
60% Written exam (open book): tba

The exam is scheduled in presence. If entrance checks are necessary for the exam due to Covid protection measures, the start of the exam may still be delayed by up to 30 minutes.
In case COVID-19 protective measures prevent examination on site, the faculty reserves the right to conduct the examination electronically during the same time slot.

An-/Abmeldung zur Leistungsüberprüfung An-/Abmelden: Belegen resp. Stornieren der Belegung via MOnA
Wiederholungsprüfung keine Wiederholungsprüfung
Skala 1-6 0,1
Wiederholtes Belegen beliebig wiederholbar
Zuständige Fakultät Wirtschaftswissenschaftliche Fakultät / WWZ, studiendekanat-wwz@unibas.ch
Anbietende Organisationseinheit Wirtschaftswissenschaftliche Fakultät / WWZ