Watch and track your favorite playlist.
Curated by: Ontology Explained: Philosophy and AI (109 videos)
A positive result from a highly accurate test feels like strong evidence. Often it's much weaker than it looks. The reason is one of the most common mistakes in statistical reasoning: the base rate fallacy. In this video, I explain what the base rate fallacy is and why it's a fallacy. (Spoiler: it's a close cousin of affirming the consequent.) Then I show how you should reason about evidence instead. We'll work through a real example from a mammogram study. The test caught every case of male breast cancer, yet a man who tests positive still very probably doesn't have it. After that, I'll give you three practical strategies for getting these questions right: - Bayes' Theorem - Picturing a crowd of 100,000 test-takers - A quick odds shortcut you can do in your head Knowing just this one anti-pattern of reasoning can help you avoid a ton of really important pitfalls in medicine, public health policy, sports scouting, and everyday life. If this helped you think more clearly, like and subscribe for more philosophy, AI, and clear thinking from an analytic philosopher. REFERENCES - Gao et al., "Breast Cancer Screening in High-Risk Men: A 12-Year Longitudinal Observational Study of Male Breast Imaging Utilization and Outcomes," Radiology, 2019. - Breast cancer in men, key statistics (American Cancer Society): https://www.cancer.org/cancer/types/breast-cancer-in-men/key-statistics.html - Base rate fallacy (Wikipedia): https://en.wikipedia.org/wiki/Base_rate_fallacy - Bar-Hillel (1980), "The base-rate fallacy in probability judgments," Acta Psychologica. - My Bayesian Epistemology Video: https://youtu.be/3s2xuqI0xJE - Affirming the Consequent: https://youtu.be/Y94_zNPZJ9c #BayesTheorem #Statistics #Philosophy