With Eric Reyes (Rose-Hulman Institute of Technology)
A traditional curriculum for an introductory statistics course builds up to the Central Limit Theorem as a model for the sampling distribution. The remainder of the course flows out of this theorem using it to develop and/or motivate inferential methods. As more instructors move toward randomization-based inference, incorporating more data visualization elements, and emphasizing computational thinking, we ask the question: is the Central Limit Theorem still central to the introductory course? In addition to sharing how sampling distributions are motivated in their own classes, the group will wrestle with questions like is the Central Limit Theorem helpful for conveying the notion of a sampling distribution and its properties? Is it distracting? Is it relevant in the world of big data?