Prof. Mats Julius Stensrud — Chair of Biostatistics at EPFL (since 2020) and Director of the Doctoral School in Mathematics at EPFL (since 2025) — is a medical doctor, Dr. philos., and Associate Professor of Statistics. He holds degrees in mathematics, medicine, and statistics, and has professional experience as a clinical physician. Before joining EPFL in 2020, he was a Fulbright Scholar and Kolokotrones Fellow at the Harvard T. H. Chan School of Public Health and a postdoctoral researcher at the University of Oslo.
His research focuses on causal inference and statistical methodology. He develops methods to address challenges in analyzing longitudinal data, such as time to event outcomes. His work puts emphasis on scientifically meaningful targets, which are studied under assumptions that are transparent and testable.
One part of his work clarifies the causal interpretation of classical survival analyses and gives the theory of separable effects, a class of causal parameters that disentangle direct and indirect effects. While working on these problems, he also became interested in questions about mechanisms, including mediation analysis. His work in this domain has been recognized with the Arthur Linder Prize (2023), the Lambert Award (2023), and the Sverdrup Prize (2024).
Some relevant articles are:
– M. J. Stensrud, M. A. Hernán. Why test for proportional hazards. JAMA, 2020
– M. J. Stensrud, J. G. Young, V. Didelez, J. M. Robins, M. A. Hernán. Separable effects for causal inference in the presence of competing events. Journal of the American Statistical Association, 2022
– M. J. Stensrud, J. M. Robins, A. L. Sarvet, E. J. Tchetgen Tchetgen, J. G. Young. Conditional separable effects. Journal of the American Statistical Association, 2023
– L. Wen, A. L. Sarvet, M. Stensrud. Causal effects of intervening variables in settings with unmeasured confounding. Journal of Machine Learning Research, 2024
– M. J. Stensrud, M. A. Hernán. Why use methods that require proportional hazards. American Journal of Epidemiology, 2025
Another line of his research studies optimal decision making and precision medicine. He develops statistical theory for dynamic treatment regimes, including regimes that can outperform both human experts and existing algorithms under explicit assumptions. This line of work also includes new statistical methods for treatment heterogeneity and a formal study of harm with implications for safe and ethical decision making.
Some relevant articles are:
– M. J. Stensrud, J. D. Laurendeau, A. L. Sarvet. Optimal regimes for algorithm assisted human decision making. Biometrika, 2024
– J. D. Laurendeau, A. L. Sarvet, M. J. Stensrud. Improved bounds and inference on optimal regimes. Journal of the American Statistical Association, 2025
– A. L. Sarvet, M. J. Stensrud. Perspectives on harm in personalized medicine. American Journal of Epidemiology, 2023
– A. L. Sarvet, M. J. Stensrud. Rejoinder to “Harm in personalized medicine — an alternative perspective”. American Journal of Epidemiology, 2025
Stensrud also works on causal inference when conventional statistical assumptions fail, for example under interference in infectious disease and vaccine studies. Recent work includes methods to identify and estimate vaccine effects when exposure is unmeasured, to separate immunologic and behavioral effects, and to quantify vaccine waning. This research is part of his SNSF Starting Grant on infectious diseases and an SNSF Project Grant on causal inference under resource constraints.
Some relevant articles are:
– M. Janvin, M. J. Stensrud. Quantification of vaccine waning as a challenge effect. Journal of the American Statistical Association, 2025
– G. Perényi, M. Stensrud. Variant specific treatment effects with applications in vaccine studies. Biometrics, 2025
– M. J. Stensrud, L. Smith. Identification of vaccine effects when exposure status is unknown. Epidemiology, 2023
– M. J. Stensrud, D. Nevo, U. Obolski. Distinguishing immunologic and behavioral effects of vaccination. Epidemiology, 2024
A fourth line of work studies practical problems in medicine and epidemiology, broadly speaking, including large scale applications. For example, he is involved in large studies on the effect of treatments against breast cancer. He also actively engages in methodology for epidemiologists, providing theoretical arguments that justify different empirical strategies and developing new ones when needed.
Some relevant publications are:
– M. Piccininni, M. J. Stensrud. Immune selection stability is a neglected property of the causal risk ratio. American Journal of Epidemiology, 2025
– A. N. Sawant, M. J. Stensrud. Explaining the sharp decline in birth rates in Canada and the United States in 2020. American Journal of Epidemiology, 2025
– M. Piccininni, M. J. Stensrud. Using negative control populations to assess unmeasured confounding and direct effects. Epidemiology, 2024
– E. Dumas, F. Jochum, F. Coussy, A. S. Hamy, A. Majdling, S. Houzard, C. Le Bihan-Benjamin, F. Reyal, P. Gougis, M. J. Stensrud. Explaining the relationships between age, endocrine therapy persistence, and risk of recurrence in hormone receptor positive early breast cancer: a nationwide cohort study. Journal of Clinical Oncology, 2025
Website, CV and google scholar profile.