Using Randomized Experiments and Common Midterm Questions to Elucidate Student Learning Trajectories from Simulation-Based Inference Curricula

• Activity Number: 287 - Classroom Teaching and Pedagogy
• Type: Contributed
• Date/Time: Wednesday, August 11, 2021 : 1:30 PM to 3:20 PM
• Sponsor: Section on Statistics and Data Science Education
• Author(s): Beth Chance* and Soma Roy and Karen McGaughey and Nathan Tintle and Todd Swanson and Jill VanderStoep
• Companies: Cal Poly - San Luis Obispo and Cal Poly - San Luis Obispo and Cal Poly - San Luis Obispo and Dordt University and Hope College and Hope College
• Keywords: Introductory statistics; Statistics education research; Simulation-based inference

Abstract

Emerging evidence over the last five years continues to point to improved student conceptual outcomes post-course in introductory statistics when learning from a simulation-based inference (SBI) curriculum compared to non-SBI curricula. These results suggest improvements regardless of instructor experience, institution type, class size, student demographics or previous experience and/or knowledge of statistical concepts. However, major gaps in our understanding remain about student learning trajectories when using SBI and how instructional and implementation choices may directly impact student outcomes. In this presentation, we will present evidence from a series of initial randomized experiments at two different institutions, designed to evaluate the impact of instructional choices on student understanding of preliminary concepts of statistical inference. We will also share results from common midterm questions from several institutions and use these to evaluate students’ developmental learning trajectories throughout the course. We highlight plans for upcoming studies and how these studies can be incorporated into the student learning experience.