The evolving mission and responsibility of statistics education

In this issue, we congratulate and celebrate the winners of two statistics education prestigious prizes that have demonstrated excellence in the teaching and learning of statistics, selected from papers in Teaching Statistics issues 1–3 in 2025. These papers include the C. Oswald George prize for best paper, entitled “Using interpolation in grade 5 to solve a mystery” by Jane Watson and Noleine Fitzallen, and the Peter Holmes prize for highlighting excellence in motivating practical classroom activity paper, entitled “A simple activity to introduce matched pairs and learning effect” by Allison Davidson. The announcements for these papers may be found in this issue, and it is my absolute pleasure as incoming editor in having the privilege of presenting these winners in this issue, as one of my first duties. Both papers, “Using interpolation in grade 5 to solve a mystery” (Watson & Fitzallen, 2025) and “A simple activity to introduce matched pairs and learning effect” (Davidson, 2025) make a significant contribution toward the evolving mission and responsibility of statistics education. These papers exemplify the importance of crafting statistical lessons that move beyond the traditions of the past, toward statistics as sense-making with data, grounded in context, reasoning, and interpretation. Watson and Fitzallen demonstrate how important skills, such as the ability to interpolate can be meaningfully integrated into learning activities for children as young as 10, which can be successfully achieved when embedded in a compelling narrative, reinforced with inquiry, and problem-solving skills development. This emphasizes the responsibility of statistics educators to further develop activities that build conceptual foundations early, rather than defer them. Davidson's paper, meanwhile, exemplifies experimental structure and comparison through an accessible matched-pairs activity, highlighting how core inferential ideas can be introduced without unnecessary complexity. Collectively, these contributions strengthen the scholarly case that statistics education must continue to engage students using a variety of contexts, and not be afraid to push the boundaries, ensuring a variety of learners continue to develop statistical reasoning skills early on in their education journey. This is central to the field's ongoing evolution, and its civic and educational responsibilities. I am delighted to present this bumper issue, packed with articles that reflect a field in transition, as statistics education continues to respond to rapid developments in computation, artificial intelligence, and the scale and scope of increasingly complex datasets. Taken together, they articulate a shared scholarly concern: how to preserve the foundations of statistical reasoning while engaging authentically with the tools, practices, and ethical questions that now shape statistical practices. Rather than treating programming, AI, or big data as add-ons, these contributions position them as integral to the evolving mission of statistics education. Several papers focus on strengthening core statistical ideas through computational engagement. “Practical programming tasks for better understanding of expectation in computer science probability courses” (Beck et al., 2026) demonstrates how programming can be used to deepen students' understanding of expectation, not by replacing theory, but by making abstract probabilistic ideas tangible through simulation and code. Similarly, “How to be ‘Choosy’: Wrangling big datasets for the classroom” (Wilkerson et al., 2026) describes the importance of data preparation using statistical judgment, showing how choices about cleaning, filtering, and structuring data are themselves central to statistical thinking. These papers reinforce the idea that computational work, when carefully designed, can support conceptual learning rather than overshadow it. An important contribution in this issue addresses the challenges posed by data mining and the use of artificial intelligence with large datasets, and the inherent biases that can occur when making statistical inferences. “The big data paradox and significance” (Faddy, 2026) reminds us that large datasets do not eliminate uncertainty or render statistical reasoning as unnecessary; instead, they demand even greater care in interpretation and inference. This perspective provides an important counterbalance to perceptions that assume more data will equate to better answers. Several other papers also engage directly with artificial intelligence and its implications for statistics education. “Why should statisticians who primarily work with structured data learn to use large language models?” (Rodrigues, 2026) presents the case for expanding statisticians' toolkits to include Large Language Models, not as replacements for statistical reasoning, but as useful technologies that assist analytical practice. “From AI to TA: How to use ChatGPT to quickly create statistics and analytics assessments” (Gordon et al., 2026) and “Harnessing generative artificial intelligence for teaching statistics in medical research: Strategies for accurate hypothesis testing” (Vilakati, 2026) develop the discussion further, emphasizing design, judgment, and the essential input of statistical expertise in AI-supported learning environments and assessments. The important topics of ethics, accessibility, and responsibility are also discussed in this issue. “A learning activity on fairness in data-driven algorithmic decision-making systems” (Schönbrodt et al., 2026) situates statistics education within broader societal debates about fairness, bias, and accountability, highlighting the role of statistical reasoning in evaluating algorithmic systems. Meanwhile, “From click to decision: VetAgroStats and code-free statistics” (Cerutti et al., 2026) explores how code-free statistical tools can broaden participation while still requiring the need for thoughtful interpretation and decision-making. Collectively, the papers in this issue advance an important scholarly conversation about what it now means to teach and learn statistics. They also advocate for statistics education that is conceptually grounded, computationally informed, ethically aware, and responsive to technological change. Statistics education is a discipline that must continue to evolve its mission and responsibilities, ensuring it adapts, not by abandoning its foundations, but by rearticulating them for a data-rich, AI-mediated world.