The aim of this course is to provide the participants with a basic understanding of empirical economics and to give them an introduction to econometrics. Building on the lecture "BA: Statistics" the participants shall be enabled to conduct empirical analysis on their own.
Analysis of economic relationships
Introduction to econometrics
Introduction to STATA
Estimating, testing and predicting in the simple and multiple regression model framework
Problems and extensions of the multiple regression model
Wooldridge, J. (2013): Introductory Econometrics. A Modern Approach. South-Western Cengage Learning.
Schira, J. (2012): Statistische Methoden der VWL und BWL. Pearson Studium.
Kohler, U., Kreuter, F. (2008): Datenanalyse mit Stata. Oldenburg Verlag.
Active participation and presentation in practical sessions
The course deals with methods of time series econometrics and focuses on applications in macroeconomics and finance. We will discuss univariate and multivariate models for stationary and non-stationary time series. In addition to the theoretical foundations, the students will apply essential tools and techniques in computer sessions using real data sets.
Univariate analysis: ARMA Models
Autoregressive distributed lag (ARDL) models
Integration and cointegration
Multivariate analysis: VAR and VECM
Identification and analysis of structural shocks: SVAR
Enders, W. (2004): Applied Econometric Time Series Analysis. Wiley.
Hamilton, J.D. (1994): Time Series Analysis. Princetion University Press.
Kirchgässner, G., Wolters, J., and Hassler, U. (2013): Introduction to Modern Time Series Analysis. Springer.
Lütkepohl, H. (2007): New Introduction to Multiple Time Series Analysis. Springer.
15.01.19: Submission of seminar paper until 12pm: 2x printed; electronic version via e-mail
18.01.19: Assignment of paper to be discussed via e-mail
24.01.19: Final presentation and discussion (room and time: tba)
Participation in all meetings
Compliance with all dates and deadlines
Seminar paper (max. 25 pages)
Discussion of another seminar paper at the final presentation
Economics: MA-FK-600, MA-W-210/220
MA: Public Policy Evaluation recommended
In this seminar we will be conducting replications of published articles. Replication of scientific findings becomes increasingly important in economics. This can mean pure re-construction and re-assessment of existing estimations, but may also include an extension of the applied methods and the use of different data. The goal of this seminar is to choose a scientific article for which data is available and replicate its estimations using the same data and methods. After checking the results, an additional sensitivity analysis is in order. This can be achieved by checking underlying assumptions, testing for effect heterogeneity or changing specifications, for example. Where possible it may also be interesting to re-run the estimations based on other data for different regions or different populations and compare the results to those in the article. This will be excellent preparation for a prospective master thesis.
The replicability of scientific results obviously depends on the availability of data. Therefore, an increasing number of economic journals demand the submission of data sets used for the estimations. Journals such as The American Economic Review, the American Economic Journal: Applied Economics, the Journal of Applied Econometrics and the Journal of Political Economy provide free public access to a large variety of data sets in their online archives. Anderson et al. (2008) predict that due to the publication of data, research will be carried out more thoroughly in the future and will be better able to correct itself and advance faster.
In this seminar, we will focus on the methods Regression Discontinuity Design and Difference-in-Differences.