Vorlesung und Übung

Grundlagen der Ökonometrie

Prof. Dr. Carsten Trenkler

Frühjahrsemester 2025

Di 13.45 – 15.15, A001 (B6, 23–25, Bauteil A)

12 Übungsgruppen, Termine und Räume finden Sie im Portal2

Vorlesung und Übung (2+2)

Deutsch

Statistik I+II 

schriftlich (90 Minuten)

6

Der Kurs gibt eine Einführung in die wichtigsten Methoden der Ökonometrie. Besprochen werden das multiple Regressionsmodell, bedingte Erwartungswertfunktion, KQ-Schätzer und seine Eigenschaften, Inferenz, nichtlineare Modellierungen, Kausalanalyse: potentielle Ergebnisse, OV-Bias, BMU-Annahme, Schätzung  kausaler Effekte, inklusive Instrumentalvariablenschätzung, sowie Zeitreihenanalyse. Neben der  Diskussion der konzeptionellen Grundlagen und der Methoden, wird die Anwendung der Methoden demonstriert und die empirisch relevanten Aspekte diskutiert. Die Vorlesung wird durch methodische und empirische Übungen im PC-Pool begleitet.

Hier finden Sie den Vorlesungsplan.

Weitere Details (inklusive Vorlesungsfolien) finden Sie auf der Ilias Seite zum Kurs.

Lecture and Tutorials

Introduction to Multiple Time Series Analysis

Prof. Dr. Carsten Trenkler

Spring Semester 2025

Bachelor

Mon 5:15pm-6:45pm in room 357; L7, 3–5, Tue 8:30am-10am in room 157, L7, 3–5

English

Grundlagen der Ökonometrie (Basic Econometrics); Statistik I+II (Statistics I + II)

6

You can find the syllabus here. Further information will be made available in the Ilias group.

Lecture and Tutorial

E806 Advanced Econometrics III (PhD)

Prof. Dr. Carsten Trenkler

Spring Semester 2025

Start: 2.4., End: 30.5.

Wed 10:15 a.m. – 11.45 a.m., Thur 8:30 a.m. – 10:00 a.m. P043 (L7, 3–5)

Alternative dates for holidays:  April 30 and May 28: 8:30–10:00am (009, L9, 1–2), May 30, 8:30–10:00am (001, L7, 3–5)

English

Advanced Econometrics I+II

Grading for this course will be based on the final exam (100 points). You can earn up to 10 bonus points if you submit solutions to the assignments that demonstrate a sufficient attempt to solve problems. To each of the three assignments a pre-announced number of bonus points is allocated. The assignments will mainly involve methodological questions but also contain some empirical questions or coding exercises. You may use any of the following (matrix) programming languages: STATA, R, or Matlab to address the latter types of questions. You will usually have a week to complete an assignment. Your solutions and programming code must be sent by email. Answers will be (partly) discussed in the tutorial sessions.

5

Part I is devoted to the analysis of panel data models. Besides discussing fixed- and random effects settings we also look into GMM/IV estimation and dynamic panel models. Part II deals with univariate time series analysis. We start with discussing theoretical foundations of time series analysis and then turn to linear models, including autoregressions. Finally, we deal with non-stationary unit root time series if time permits.

The course material will be provided via the Ilias group.

Lecture

Prof. Dr. Carsten Trenkler

Autumn Semester 2024

PhD

Monday, 3:30 to 5:00pm (L7, 3–5, P043) and Thursday, 10:15 to 11:45am (L7, 3–5, 410)

English

E703, E803, E806 Advanced Econometrics I – III

Assignments (30%), presentation (30%), paper (40%)

9

The course will focus on multivariate time series models. After reviewing a few general concepts from probability theory and time series analysis, we will first deal with stable VAR models and their use for Granger causality, impulse response analysis, historical decompositions, and forecast error variance decompositions. To this end, we will also discuss important issues on asymptotic- and bootstrap-based inference.

Then, we deal with univariate unit root processes and introduce the relevant asymptotic approach for this set-up. In a next step, we turn to a treatment of multivariate unit root processes which are assumed to be integrated of order one, I(1). Afterwards, we briefly introduce the concept of cointegration and learn how cointegration can be integrated into VAR framework leading to a so-called vector error correction model (VECM). As cointegration is not that popular anymore in empirical work, we will only summarize how to do appropriate inference in potentially cointegrated VARs with I(1) variables.

If time permits, I would like to give an overview on estimating high-dimensional VARs and factor models in the last part of the course.

The course both addresses asymptotic analyses as well as implementation issues. Accordingly, tutorial sessions are also devoted to coding and empirical problems besides addressing theoretical problems.

In the last part of the course, participants introduce or discuss in more details (further) model classes by giving presentations and writing a paper. This year, I will provide a set of recent papers on network analysis using multiple time series approaches. This shall give an impression and overview on a recent strand in the literature.

Our course is complementary to the course offered by Matthias Meier. While the latter course focus on structural modeling approaches from an applied macro perspective, we take an econometric approach on multiple time series frameworks.

• Preliminary Syllabus
• Further material can be found in the course's Ilias group once set up.