This talk is a friendly introduction to the formal model of learning from new evidence called "Bayesian updating". The Bayesian rule for updating is the most general account of how evidence works, encompassing and explaining the (limited) usefulness of statistical ideas like p-values and confidence intervals. This talk will show you how to do Bayesian updating in your head, using a simple formulation equivalent to the much more unwieldy equation known as 'Bayes' theorem.'
David Manley is an associate professor of philosophy at the University of Michigan, Ann Arbor. His research has been mainly about semantics, ontology, probability, and evidence. But lately He has been thinking about conditions for rationality and well-being—not just for individual people, but also for groups, animals, and other cognitive systems.
This talk was taken from EA Student Summit 2020. Click here to watch the talk with the PowerPoint presentation.