James Friedrich, Professor of Psychology
Title: The “New Statistics”: Improving Statistical Practices to Benefit Science and the Public
Abstract: Have you ever wondered what it means to say something is “statistically significant”? Would it surprise you to know that many professionals are nearly as confused as the general public? Natural and behavioral scientists have long relied upon the questionable practice of null hypothesis significance testing (NHST), and its logic and language have come to permeate public (mis)understandings of statistical evidence. Newer data analytic approaches emphasizing margins of error, strength of relationship, and the synthesis of multiple studies through meta-analysis are moving from highly recommended to mandatory practices in scholarly outlets. This talk discusses some of the common abuses and misconceptions of the “old statistics” and highlights how the long-overdue transition to these “new statistics” will better serve science and the general public. Explanations will be more conceptual than mathematical, highlighting benefits both to data analysts and research consumers. The role of the QUAD center in supporting these best practice with students and faculty will also be discussed.
Please feel free to invite students to attend this talk.
We look forward to seeing you there.
Doreen Simonsen and Daniel Rouslin
Faculty Colloquium Coordinators