Syllabus: Survey Statistics

Qualification aims: 
This course is designed to provide an overview over key concepts and methods used in survey statistics. The course will cover various aspects of sampling, including sampling frames, types of (random) samples, and strategies to avoid unit non-response. The importance of survey weights, including design weights, non-response weights, and post-stratification, will also be discussed. Additionally, the course will cover item non-response and mul6ple imputation, as well as the chances of machine learning in survey statistics, The course is accompanied by a tutorial that also includes exercises with statistical software.

Content: 
Modern statistical methods, e.g. survey statistics, statistical inference, machine learning, multivariate statistics, non- and semi-parametric modelling.

Course language: English

Workload: 180 hours (6 LP)

Structure of the course:
1. Total survey error
2. Design-based approach
3. Sampling strategies
4. Model-based approach
5. Non response
6. Machine learning for survey statistics
7. Variance estimation
8. Small area estimation

Literature:
Engel, U., & Schmidt, B. (2014) Unit- und Item-Nonresponse. In: Baur, N., Blasius, J. eds. Handbuch Methoden der empirischen Sozialforschung.
Wiesbaden: Springer, p.331-348.

Groves, R. M. (2009). Survey methodology (2nd ed.). Wiley.

Hastie, T., Tibshirani, R., & Friedman, J. (2009). The elements of statistical learning: Data mining, inference, and prediction (2nd ed.). Springer New York, NY. https://doi.org/10.1007/978-0-387-84858-7.

Lehtonen, R., & Pahkinen, E. (2003). Practical methods for design and analysis of complex surveys. John Wiley & Sons, Ltd. https://doi.org/10.1002/0470091649.

Rao, J.N.K., & Molina, I. (2015). Small area estimation. John Wiley & Sons, Inc., https://doi.org/10.1002/9781118735855