Scientific Coordination
Sebastian E. Wenz
Tel: +49 221 47694-159
Tel: +49 221 47694-159
Administrative Coordination
Jacqueline Schüller
Tel: +49 0221 47694-160
Tel: +49 0221 47694-160
Please wait...
Course 4: (Non-)Probability Samples in the Social Sciences
About
Location:
Online via Zoom
Online via Zoom
Course duration:
10:00-17:00 CEST
General Topics:
Course Level:
Format:
Software used:
None
Duration:
Language:
Fees:
Students: 500 €
Academics: 750 €
Commercial: 1500 €
Keywords
Additional links
Lecturer(s): Carina Cornesse, Olga Maslovskaya
Course description
The main objective of the course is to provide students with a full overview of the history, theoretical foundations, critical arguments, and accumulated empirical evidence surrounding the debate about probability and nonprobability sample surveys. A focus will be on real-world examples of why and how the choice of sample type matters, including topics such as election polling debacles, mispredictions during the pandemic (e.g., willingness to get vaccinated), and the role that surveys can have in supporting versus debunking fake news.
In addition to discussing these topics, the course will provide students with an in-depth understanding of the conditions under which probability and nonprobability samples can provide useful data to answer social scientific research questions (e.g., Total Survey Error framework adaptations, fit-for-purpose designs, causal inference logic), including hands-on recommendations and exercises on how to design your own (hypothetical) research study.
Furthermore, we will discuss the benefits and challenges of different approaches to probability and nonprobability sampling (e.g., simple vs. stratified random sampling, snowball vs. respondent-driven sampling, social media and river sampling) as well as recent insights on sample weighting and data integration techniques (e.g., propensity score weighting and blended calibration). All material and discussions will be hands-on and intuitive.
A detailed syllabus with course times and literature will soon be available for download here.
Target group
Participants will find the course useful if:
Learning objectives
By the end of the course participants will:
Organizational structure of the course
This is a five-day course with a total amount of 30 hours of virtual class time. Participants can expect a mix of interactive teaching, group exercises, and opportunity for individual consultation. Exercises are designed to deepen the understanding of the course material and to apply it to hypothetical and real-world research settings. This will not require using any statistical software (although participants will have the opportunity to work with data voluntarily using their preferred software). To get the most out of the course, students are strongly encouraged to participate pro-actively in small-group projects, present their thoughts and work output in class, and critically discuss the course material with the lecturer and classmates.
Prerequisites
Software and hardware requirements
None