FALL 2020 SECTION NEXT workshop

September 19th, 9:30am-4:30pm, Online

9:30-9:45 Welcome and Introductions

9:45-10:45 Resampling Session 1 - Carolyn Cuff, Westminster College and Juniata College

10:45-11:00 Break

11:00-12:00 Resampling Session 2 - Carolyn Cuff

12:00-1:30 Lunch Break

1:30-3:00 Panel Discussion: "Active Learning Strategies for Remote Teaching", Rena Levitt (Minerva University), Kuei-Nuan Lin (Penn State Allegheny), Virgil Pierce (University of Northern Colorado), Stanley Smith (Penn State University)

3:00-4:30 Further discussion and sharing

Social hour following the meeting

Resampling: What It Is and How You Can Incorporate it into Your Introductory Statistics Course

Carolyn Cuff, Westminster College and Juniata College

Randomization and bootstrapping are forms of resampling and relatively new to introductory statistics. Research has shown that teaching the concepts helps students understand the inference process. Come and learn about resampling, why it helps students understand inferential statistics, and work through two classroom ready modules. Please have a deck of cards ready for the second session.

Session 1 – An introduction to resampling and simulation based inference. We consider the inclusion of sampling distributions in the introductory course and how they are supposed to inform the central limit theorem. Then we turn to the distribution of the sample and how it informs us about population and how we can use it to create the bootstrap distribution, another type of sampling distribution. A set of apps including one that can be used to introduce students to bootstrap distributions will be explored.

Session 2 – Two classroom ready simulation based inference modules will be presented. One will use bootstrapping to create a confidence interval for the proportion of orange Reese’s pieces in a Halloween size snack pack. The second will use a randomization distribution to test a hypothesis about the effectiveness of a new drug. We explore two additional sets of apps for simulation based inference.