Doing Research in Statistics Education: More Than Just Data

As teachers of statistics we know the fundamental components of statistical enquiry, be it classical or exploratory. When we turn the focus on ourselves as statistics educators, we run the risk of forgetting some of the fundamental principles of good research – principles that are broader than carrying out statistical significance tests. In this talk I want to present some examples of research in statistics education to illustrate the stages and outcomes that contribute to results that have a scholarly impact on the statistics education community. As a single teacher with a good idea on how to teach “confidence intervals,” I do not expect anyone to pay much attention to me. If I can, however, place my ideas in the context of others’ ideas or research on teaching confidence intervals; conduct a study – maybe a case study or a controlled experimental design – that is valid for considering the issue I want to promote in teaching about confidence intervals; and have my results refereed by peers in the field; then I can expect people to pay attention to me. Research in statistics education is more broadly based than classical statistics applied to science. So, why do we do research in statistics education? Because research tells us something new and because hopefully research tells us something important. No matter how good the research is, however, how the story is told is what convinces us of the newness and importance. It must also convince us that the research is valid and rigorous in its context. There are many types of research in statistics education represented at this conference. I only have time to give examples of three. They come from areas I will call theoretical, qualitative and quantitative. These terms reflect the perspectives on dealing with the data collected. There are many types of content that could be used as a focus for these three kinds of research but I am going to pick three areas in which I have been involved with fellow researchers around the world for the past few years: statistical reasoning, statistical thinking, and statistical literacy [SRTL]. Joan Garfield, who could not be with us at this conference, intended to speak on these themes. She helped organize two forums on SRTL and is currently editing a book on the topic. What we want to do today is to use these three themes to illustrate the three types of research: statistical thinking for a theoretical research perspective, statistical reasoning for a qualitative research perspective, and statistical literacy for a quantitative research perspective. I will have to simplify some details so I encourage you to trace the original sources.