Here are videos of some of my presentations and podcast interviews:

• A Selective History of Political Polling and Election Forecasting (Presented at Columbia University, 30 Oct 2025)

• Bayesian Workflow (Presented at the Isaac Newton Institute, 26 Jun 2025)

• Generalizing for Sampling and Causal Inference (Joint Program in Survey Methodology Distinguished Lecture, 28 Apr 2025)

• Bayesian Workflow (Conversation with Charles Margossian for the MetrumRG podcast, 22 Oct 2024)

• Tough Choices in Election Forecasting: All the Things That Can Go Wrong (Presented at the Washington Statistical Society, 11 Oct 2024)

• The Political Content of Unreplicable Research (Presented at the Stanford Classical Liberalism Seminar, 3 Oct 2024)

• Fooling Yourself Less: The Art of Statistical Thinking in AI (Conversation for the High Signal podcast, 18 Sep 2024)

• Effective Number of Parameters in a Statistical Model (Presented at Osaka University, 10 Sep 2024)

• Holes in Bayesian Statistics (Presented at the International Society for Bayesian Analysis meeting, 3 Jul 2024)

• Beyond the Black Box: Toward a New Paradigm of Statistics in Science (Presented at the Alan Turing Institute, 20 Jun 2024)

• It's About Time (Presented at the New York R Conference, 16 May 2024)

• Active Statistics, Two Truths and a Lie (Presented at the Learning Bayesian Statistics podcast, 2 Apr 2024)

• Learning from Mistakes (Presented at an American Statistical Association webinar, 30 Jan 2024)

• Better than Difference-in-Differences (Presented at Online Causal Inference Seminar, 19 Sep 2023)

• Educating the Future Statisticians: Bringing Our Teaching Up-to-date (Presented at University College London, 13 June 2023)

• Social Science: From Prediction to Modeling to Understanding (Presented at Collège de France, 29 June 2022)

• When You Do Applied Statistics, You're Acting Like a Scientist. Why Does This Matter? (Presented at New York R Conference, 9 June 2022)

• Bayesian Methods in Causal Inference and Decision Making (Presented at Criteo Labs, 7 Mar 2022)

• Discussion of Ivermectin Trials for Covid-19 (Conversation with Greg Kellogg, 4 Mar 2022)

• Modeling and Poststratification for Descriptive and Causal Inference (Presented at CUNY Graduate School of Public Health and Health Policy, 2 Feb 2022)

• Wrong Again! 30+ Years of Statistical Mistakes (Presented at New York R Conference, 10 June 2021)

• Statistics and American Politics (Presented at The Great Battlefield podcast, 31 May 2021)

• Information, Incentives, and Goals in Election Forecasts (Presented at the DIMACS Workshop on Forecasting, 1 Apr 2021)

• The Most Important Statistical Ideas in the Past 50 Years (Presented at the Boston chapter of the American Statistical Association, 17 Mar 2021)

• Election Forecasting: How We Succeeded Brilliantly, Failed Miserably, or Landed Somewhere in Between (Presented at Dana-Farber Cancer Institute, 10 Nov 2020)

• Modeling the US Presidential Elections (Presented at Learning Bayesian Statistics podcast, 1 Nov 2020)

• Reflections on Breiman's Two Cultures of Statistical Modeling, and An Updated Dynamic Bayesian Forecasting Model for the 2020 Election (Presented at UCLA, 13 Oct 2020)

• Election Forecasts: The Math, the Goals, and the Incentives (Presented at Cornell Center for Applied Math, 18 Sep 2020)

• Truly Open Science: From Design and Data Collection to Analysis and Decision Making (Presented at New York R Conference, 13 Aug 2020)

• 100 Stories of Causal Inference (Presented at Online Causal Inference Seminar, 4 Aug 2020)

• Regression and Other Stories (Presented at Learning Bayesian Statistics podcast, 30 Jul 2020)

• Statistics is the Least Important Part of Data Science (Presented at Artists of Data Science podcast, 23 Jul 2020)

• Data, Modeling, and Uncertainty Amidst the Forking Paths (Presented at The Filter podcast, 21 Jul 2020)

• Embracing Variation and Accepting Uncertainty (Presented at Australian Research Council Training Centre in Data Analytics for Resources & Environments, 20 Jul 2020)

• Scientific Reasoning for Practical Data Science (Presented at Philosophy of Data Science podcast, 24 Jun 2020)

• Embracing Variation and Accepting Uncertainty: Implications for Science and Metascience (Presented at Metascience Symposium, 6 Sep 2019)

• Solve All Your Statistics Problems Using P-Values (Presented at New York R Conference, 9 May 2019)

• Significanct Science (Presented at The Neoliberal Podcast, 18 Jan 2019)

• Bayesian Workflow (Presented at University of Vienna, 9 Nov 2018)

• Election Forecasting and Polling (Presented at Datacamp, 8 Oct 2018)

• Evidence-Based Practice Is a Two-Way Street (Presented at Society for Research on Educational Effetiveness conference, 28 Feb 2018)

• Bayes, Statistics, and Reproducibility (Presented at Rutgers University, 29 Jan 2018)

• Data Science Workflow (Presented at PyData, New York, 2017)

• The Statistical Crisis in Science and How to Move Forward (Presented at Columbia University, 13 Nov 2017)

• Theoretical Statistics is the Theory of Applied Statistics: How to Think About What We Do (Presented at New York R Conference, 21 Apr 2017)

• Social Science, Small Samples, and the Garden of the Forking Paths (Presented at EconTalk podcast, 20 Mar 2017)

• Introduction to Bayesian Data Analysis and Stan (Presented for Generable, 25 Oct 2016)

• Crimes Against Data (Presented at the ERCC Research Methods Festival, 5 July 2016)

• The Political Impact of Social Penumbras (Presented at New York R Conference, 8 Apr 2016)

• Taking Bayesian Inference Seriously (Presented at Harvard University, 2016)

• Why Do Americans Vote the Way They Do? (Presented at Rationally Speaking podcast, 11 Nov 2015)

• But When You Call Me Bayesian, I Know I'm Not the Only One (Presented at New York R Conference, 24 Apr 2015)

• Living with Uncertainty but Still Learning (Presented at Simons Foundation, New York, 10 Sep 2014)

• Weakly Informative Priors (Presented at AIStats conference, 23 Apr 2014)

• Active Learning in Statistics Classes (Presented for Quantitiative Methods teaching project, 24 Oct 2013)

• Creating Structured and Flexible Models: Some Open Problems (Presented at the New York City R meetup, 7 Oct 2010)

• Why We (Usually) Don't Have to Worry About Multiple Comparisons (Presented at a workshop at Columbia University on estimating effects and correlations in neuroimaging data, 15 July 2009)

• Red States, Blue States, and Political Polarization (Presented at the 10th anniversary celebration of the Center for Statistics and Social Sciences, University of Washington, 5 June 2009)

• Rich State, Poor State, Red State, Blue State: Why Americans Vote the Way They Do (Presented at the Authors@Google series, Mountain View, California, 20 March 2008)

Back to Andrew Gelman's homepage.