I will cover, at a relatively high level, a set of recent conceptual advances, and what I view is their utility to the sciences. These will range from universal inference (hypothesis testing), online control of false discoveries (multiple hypothesis testing), e-values (sequential alternative to p-values), confidence sequences (aka how to peek at your data as you collect it), masking (aka how to interact with your data after you've collected it) and conformal prediction (uncertainty quantification for black-box machine learning prediction methods).
The seminar will be done remote only.
M. Girone, M. Elsing, L. Moneta, M. Pierini
Event co-organised with the PHYSTAT Committee