Please note: This course will be taught in hybrid mode. Hybrid delivery of courses will include synchronous live sessions during which on campus and online students will be taught simultaneously.
Yanna Krupnikov’s research focuses on political communication. Her most recent research considers variation in political attention and political expression. This research on attention is the topic of her most recent book, The Other Divide.
This course will focus on advanced topics in survey design and analysis. Topics covered include different approaches to sampling, the effects of survey mode, and tools for analysing and enriching survey data, including question-wording, measurement and treatment validity, measurement of reported behaviour as well as social network studies. The course will also focus on designing and analysing survey experiments and current debates about the use of varying samples in these experiments. In addition, the course will consider various types of available samples, and the trade-offs in using certain sample types.
Participants will gain an advanced understanding of best practices for analysing survey data and designing and analysing various types of survey experiments. Participants will also gain hands-on experience in analysing survey data and constructing and analysing survey experiments. Participants can also pose questions about their own ongoing survey research and data projects.
Course participants who want to take part in the hands-on analysis components of the course should have some familiarity with Stata or R. Participants who want to take part in the analysis components should also be comfortable with descriptive statistics and should have at least some familiarity with OLS regression. No additional background readings are required for this course.
The course will cover the following topics:
- Foundations of survey response
- Sampling and Weights
- Item non-response and other survey response biases
- Analytic approaches to survey data
- Social network measures in surveys
- Moderators and Mediators
- Survey experiments: design, analysis and samples
Background knowledge required
OLS = moderate
Stata = elementary
R = elementary
Linear Regression = Moderate