This course continues the sequence in statistical modeling, helping students build a more diverse and sophisticated data analysis toolkit. In the first half of the course, we introduce a new perspective on studying causes and effects in social science and present various strategies to uncover causal relationships using statistical tools, from conditioning on observables (regression and matching) to the use of natural experiments (instrumental variables and regression discontinuity). The second half of the course covers other essential tools for analyzing data from the social world, including strategies for measuring theoretical constructs, analyzing time series and categorical data, and creating beautiful and informative data visualizations. All lectures divide time between theory and application, while labs and assignments emphasize hands-on data analysis with R.
Instructor
- Asya Magazinnik , Professor of Social Data Science