In this seminar, methods of advanced quantitative methods for cross-sectional analysis are taught.
Topics of the seminar are:
A. Properties of statistical estimators
B. Regression modelling:
- Linear regression (advanced level)
- Nonlinear models / generalized linear models
- Poisson regression
- Logit and probit model
- Ordered response models (ordered probit / logit model)
- Multinomial response models (multinomial logit model)
C. Survey design and survey weights (and how to use them)
In this context, we will also talk about model selection, transformation of variables, heteroscedasticity, and endogeneity.
We will use the statistical software R (with R-Studio as editor) in the seminar.
Either 5 or 10 ECTS points can be achieved in the course.
For 5 points, all exercises must be worked on during the seminar and handed in after the seminar.
For 10 points, the written elaboration of a research project (max. 12 pages) is necessary, for which the student already brings a topic, a question and an associated data set as a prerequisite.
Termin 4.2.2022 vsl. digital
|
