Search for: All records

With the rise of the popularity of Bayesian methods and accessible computer software, teaching and learning about Bayesian methods are expanding. However, most educational opportunities are geared toward statistics and data science students and are less available in the broader STEM fields. In addition, there are fewer opportunities at the K-12 level. With the indirect aim of introducing Bayesian methods at the K-12 level, we have developed a Bayesian data analysis activity and implemented it with 35 mathematics and science pre-service teachers. In this article, we describe the activity, the web app supporting the activity, and pre-service teachers’ perceptions of the activity. Lastly, we discuss future directions for preparing K-12 teachers in teaching and learning about Bayesian methods. 

What do we know about data science learning at the grades K–12 (precollegiate) level? This article answers this question by using the notion of agency to provide a framework to review the diverse research agendas and learning environments relevant to data science education. Examining research on data science education published in three recent special issues, we highlight key findings from scholars working in different communities using this lens. Then, we present the results of a co-citation coupling analysis for articles published in one of three recent data science education special issues with research spanning various levels and contexts. This co-citation analysis showed that while there are some common touchpoints, research on data science learning is taking place in a siloed manner. Based on our review of the literature through the lens of agency and our analysis, we discuss how the data science education community can synthesize research across disciplinary and grade-level divides.