Our Findings from Using Randomization-Based-Methods Curricula

• Activity Number: 293
• Type: Contributed
• Date/Time: Tuesday, July 31, 2012 : 8:30 AM to 10:20 AM
• Sponsor: Section on Statistical Education
• Author(s): Soma Roy*+ and Beth Chance and Karen McGaughey and Allan Rossman
• Companies: California Polytechnic State University and California Polytechnic State University and California Polytechnic State University and California Polytechnic State University
• Keywords: assessment ; student attitude ; conceptual understanding ; introductory statistics

Abstract

We, the authors, have been using a randomization-based approach to teach concepts and methods of statistical inference in our introductory statistics courses at Cal Poly, for the past several quarters. In this paper, we present our findings about student understanding of fundamental concepts of statistical inference, as well as attitude towards the discipline of Statistics, for students in such courses. In particular, we focus on student understanding of the interpretation and evaluation of a p-value, sampling variability, and the interpretation of "confidence level" in terms of repeated sampling. Various test items (including items from CAOS and MOST), and surveys have been used, and new items continue to be developed and used to collect data on students' conceptual understanding, progress through course content, and attitudes towards Statistics and learning Statistics.