Friday, March 28, 2025
Lecture room B6
Institute for Exact Sciences
Sidlerstr. 5
CH-3012 Bern
14:30-15:20 h
Causality and Beyond (with applications in FDA, GLM and REM)
Ernst-Jan C. WIT (Università della Svizzera italiana, Lugano)
As R.A. Fisher understood, causal discovery is feasible when controlled experiments on the system of interest can be conducted. Even in the absence of controlled human interventions, reality often provides natural experiments, offering observations of the same system under slightly shifted conditions. Rather than merely pooling such information, we propose an approach that minimizes future prediction error by optimizing a functional that accounts not only for pooled risk but also for risk differentials across settings. We demonstrate how this method extends beyond the linear regression framework into functional data analysis (FDA). By adjusting the squared risk functional to the Pearson risk, we further generalize the approach to the highly practical setting of generalized linear models (GLMs). Finally, we illustrate the applicability of this framework to dynamic network modelling, specifically in the context of relational event models (REMs), showcasing its potential in real-world applications where observational data naturally encode causal variation. This is joint work with Lucas Kania (Carnegie Mellon), Philip Kennerberg (USI), Melania Lembo (USI) and Veronica Vinciotti (Trento).
