Things you didn’t know you needed: Graphical Causal Models
Dr Julia Rohrer
University of Leipzig
Correlation does not imply causation -- but correlations are often all we can get. In this session, I will provide a brief non-technical introduction to graphical causal models. These models are a powerful tool for researchers working with observational data, but also for experimentalists: A broad range of common inference problems (e.g., mediation analysis, missing data, generalization across populations and settings) can be greatly clarified through a causal lens. Psychologists are fond of lists of threats to validity, but maybe it is time to move on to a more systematic and transparent approach in which we explicitly spell out licensing assumptions.
About the speaker
Julia Rohrer finished her doctoral degree as a fellow of the International Max Planck Research School on the Life Course in 2019. A personality psychologist by training, her work covers a broad range of topics, including the effects of birth order, age patterns in personality, and the determinants and correlates of subjective well-being. Her methodological interests include causal inference on the basis of observational data, data analytic flexibility, and research transparency.
Zoom link available via MSPS School Colloquium mailing list. To be added to this list or for the link to this talk, please email Dr. Elise Kalokerinos.