Technology Innovations in Statistics Education

Conducting inference is a cornerstone upon which the practice of statistics is based. As such, a large portion of most introductory statistics courses is focused on teaching the fundamentals of statistical inference. The goal of this study is to make a formal comparison of learning outcomes under the traditional and simulation-based inference curricula. A randomized experiment was conducted to administer the two curricula to students in an introductory statistics course. Students of the simulation-based curriculum were found to have improved learning outcomes on topics in statistical inference; however, a clear violation of between-student independence due to group administration of curriculum treatments casts considerable doubt on the statistical significance of these results. A simulation study is used to demonstrate the volatility of Type I error rates in educational studies where classroom level covariance structures exist by comparisons are made on the student level.

Statistical literacy skills and technological literacy skills are becoming increasingly entwined as the practice of statistics shifts toward more reliance on the power of technology. More and more, statistics educators suggest reforming introductory college statistics courses to include more emphasis on technology and modeling. But what is the impact of such a focus on student learning? This research examines a small sample of students. The students received a reform-oriented curriculum focused on modeling and simulation using TinkerPlots^TM technology. The data reported here is from students written work at the end of the term on their final assessment. They had access to TinkerPlots^TM for the assessment and we share the ways they used the technology to create statistical models. This work provides insights into the ways students’ construct models and how they interpret the models they construct within the context of the original statistical problem they were given. We describe how the technology used in this reform class appeared to frame students’ ways of constructing a statistical model. We also discuss challenges of this approach for student thinking and share implications for teaching and future research.

Technology plays a critical role in supporting statistics education, and student comprehension is improved when simulations accompanied by dynamic visualizations are employed. Many web-based teaching tool applets programmed in Java/Javascript are publicly available (e.g., www.rossmanchance.com, www.socr.ucla.edu). These provide a user-friendly interface which is accessible and appealing to students in introductory statistics courses. However, not all statistics educators are fluent in Java/Javascript and may not be able to tailor these apps or develop their own. Shiny, a web application framework for R created by RStudio, facilitates applet development for educators who are familiar with R. We illustrate the utility, convenience, and versatility of Shiny through our collection of 17 freely available apps covering a range of topics and levels (found at www.statistics.calpoly.edu/shiny). Our Shiny source code is publicly available so that anyone may tailor our apps as desired. We provide feedback on how our apps have been used in statistics classes including some challenges that were encountered. We also discuss feasibility on building, launching, and deploying Shiny apps. A brief tutorial on installing and using Shiny is provided in the appendix. Some teaching materials based on our Shiny apps are also included in the appendix.