Using Interactive Shiny Applications to Facilitate Research-Informed Learning and Teaching

ABSTRACT

In this article we discuss our attempt to incorporate research-informed learning and teaching activities into a final year undergraduate Statistics course. We make use of the Shiny web-based application framework for R to develop “Shiny apps” designed to help facilitate student interaction with methods from recently published papers in the author's primary research field (extreme value theory and applications). We also replace some lectures with dedicated “reading group tutorials.” Here, students work in small groups to discuss and critique carefully selected papers from the field. They are also encouraged to use our Shiny apps to implement some of the methods discussed in the papers with their own data, for use in project work. We attempt to evaluate our innovation by comparing students' responses in open-ended data analysis work, and work requiring the interpretation of methods in a recently published paper, to those of students who took the same course two years earlier when our Shiny apps were not available and when research tutorials were not used. This comparison, along with results from a student questionnaire, gives us some confidence that our methods have benefited students, not only in terms of their ability to understand and implement advanced techniques from the recent literature but also in terms of their confidence and overall satisfaction with the course.

KEYWORDS:

• Extreme values
• Research-informed learning and teaching
• Statistics education
• Shiny

Acknowledgments

The author would like to thank Keith Newman for his support in developing the Shiny apps discussed in this article, as well as the undergraduate interns who worked under Keith's supervision: Amy Green, Theo Roe, and Emma Bradley. We also thank the Editors and reviewers for their comments and suggestions, which we feel has greatly improved the manuscript.

Supplementary Material

The appendices for this article can be accessed as supplementary material on the publisher's website.

Notes

¹ The course discussed in this article was attended by students working at Masters level. Although we might not expect RILT activities to have such a natural place in lower level Statistics courses, there might be a case for replacing standard lectures with more interactive sessions in these courses too, for example to promote a deeper understanding of more basic concepts (see, e.g., Everson and Garfield 2008). However, we think more careful consideration would be needed here to identify the course material to be taken out of lectures