About

Our Themes

Whether studying educational outcomes or public health initiatives, our research partnerships place a strong emphasis on equity and fairness. Learn more about our work across the globe by exploring each research theme.

Back to All Events
2025/01/1737413530997.jpeg

Stijn Vansteelandt on Seminar Series: Causal Inference and Data Science for Improved Policy

On February 3, 2025, DSI will host the presentation titled “Assumption-Lean (Causal) Modeling,” marking the fourth talk of our seminar series that encourages research collaboration among data scientists, causal inference experts, and applied researchers. This series is funded through the DSI Emergent Data Sciences Program competition, and co-led by Professors Linbo Wang (Departments of Statistical Sciences and Computer Science), Gustavo J. Bobonis, Raji Jayaraman, and Ismael Mourifié (Department of Economics) at the University of Toronto.

Speaker

Stijn Vansteelandt,

Professor of Statistical Methodology, Department of Applied Mathematics, Computer Science and Statistics, Ghent University
 

 

Featured Research

Prof. Vansteelandt will delve into assumption-lean modeling, a paradigm that addresses the limitations of traditional inference in (semi-) parametric models. These models often rely on correct specification, which can lead to bias in causal modeling due to unacknowledged uncertainty and misspecification. Assumption-lean modeling rethinks this trade-off by combining data-adaptive predictions with projections onto specific model parameters. This approach ensures interpretability and validity even under misspecification, using debiased machine learning techniques to minimize bias and account for model uncertainty.

Related Past Events