The International Methods Colloquium hosted a roundtable discussion on reproducibility and a recent proposal to impose a stricter threshold for statistical significance on October 27, 2017. The discussion is motivated by a paper, "Redefine statistical significance," recently published in Nature Human Behavior (available at this link). Panel participants include: Daniel Benjamin, Associate Research Professor of Economics at the University of Southern California and a primary co-author of the paper "Redefine statistical significance" in Nature Human Behavior, as well as many other articles on inference and hypothesis testing in the social sciences. Daniel Lakens, Assistant Professor in A

International Methods Colloquium talk on October 20, 2017. Arthur Spirling of NYU presented a talk entitled "Text Preprocessing for Unsupervised Learning: Why It Matters, When It Misleads, and What to Do about It." The presentation slides are available at this link. #video