Holistic data science education places data science in the context of real world applications, emphasizing the purpose for which data were collected, the pedigree of the data, the meaning inherent in the data, the deploying of sustainable solutions, and the communication of key findings for addressing the original problem. As such it spends less…

Many data science applications involve generating questions, acquiring data and preparing it for analysis--be it exploratory, inferential, or modeling focused--and communicating findings. Most data science curricula address each of these steps as separate units in a course or as separate courses. Open-ended term projects, however, allow students…

This paper describes the role of data and task context in young children's interpretation of and reasoning about data tables. A design-based descriptive study was conducted with fourteen 5-year-old children in their first year of formal schooling. A picture storybook provided the data context for a data modelling activity that focused on…

This study examines modelling with machine learning. In the context of a yearlong data science course, the study explores how upper secondary students apply machine learning with Jupyter Notebooks and document the modelling process as a computational essay incorporating the different steps of the CRISP-DM cycle. The students' work is based on a…

Statistical literacy is a skill that will be required by all students, but only limited insights exist into how it can be developed in middle schools. Research is required that identifies design principles and provides didactic materials for developing statistical literacy in actual middle school classrooms, meaning classrooms in which statistics…

Data science surrounds us in contexts as diverse as climate change, air pollution, route-finding, genomics, market manipulation, and movie recommendations. To open the "data-science-black-box" for lower secondary school students, we developed a data science teaching unit focusing on the analysis of environmental data, which we embedded…

The influx of data and the advances in computing have led to calls to update the introductory statistics curriculum to better meet the needs of the contemporary workforce. To this end, we developed the COMputational Practices in Undergraduate TEaching of Statistics (COMPUTES) instrument, which can be used to measure the extent to which computation…

The African Data Initiative started as a crowd-sourced campaign to improve the teaching of statistics in African universities. The analysis of climate data provides one suitable context to illustrate ideas that lead to a radical new form of teaching. The problem within the context comes first, the technicalities are largely reduced -- mathematics…

Group comparisons offer students opportunities to reason about many fundamental statistical concepts like center, variation, or distribution. When doing such activities using large, real datasets, technology becomes an essential tool for exploring the data. With its large variety of features and its user-friendly handling, TinkerPlots™--as a…

Connecting data and chance is fundamental in statistics curricula. The use of software like TinkerPlots can bridge both worlds because the TinkerPlots Sampler supports learners in expressive modeling. We conducted a study with elementary preservice teachers with a basic university education in statistics. They were asked to set up and evaluate…

In British social science degree programmes, methods courses have a bad press, and statistics courses in particular are not well-liked by most students. A nationally-coordinated, strategic investment in quantitative skills training, Q-Step, is an attempt to address the issues affecting the shortage of quantitatively trained humanities and social…

This article discusses five papers focused on "Research on Reasoning about Variation and Variability", by Hammerman and Rubin, Ben-Zvi, Bakker, Reading, and Gould, which appeared in a special issue of the "Statistics Education Research Journal" (No. 3(2) November 2004). Three issues emerged from these papers. First, there is a link between the…

Variability stands in the heart of statistics theory and practice. Concepts and judgments involved in comparing groups have been found to be a productive vehicle for motivating learners to reason statistically and are critical for building the intuitive foundation for inferential reasoning. The focus in this paper is on the emergence of beginners'…

New software tools for data analysis provide rich opportunities for representing and understanding data. However, little research has been done on how learners use these tools to think about data, nor how that affects teaching. This paper describes several ways that learners use new software tools to deal with variability in analyzing data,…