A Guide to Teaching Data Science

Demand for data science education is surging and traditional courses offered by statistics departments are not meeting the needs of those seeking training. This has led to a number of opinion pieces advocating for an update to the Statistics curriculum. The unifying recommendation is computing should play a more prominent role. We strongly agree with this recommendation, but advocate the main priority is to bring applications to the forefront as proposed by Nolan and Speed (1999). We also argue that the individuals tasked with developing data science courses should not only have statistical training, but also have experience analyzing data with the main objective of solving real-world problems. Here, we share a set of general principles and offer a detailed guide derived from our successful experience developing and teaching a graduate-level, introductory data science course centered entirely on case studies. We argue for the importance of statistical thinking, as defined by Wild and Pfannkuck (1999) and describe how our approach teaches students three key skills needed to succeed in data science, which we refer to as creating, connecting, and computing. This guide can also be used for statisticians wanting to gain more practical knowledge about data science before embarking on teaching an introductory course.

💡 Research Summary

The paper addresses the rapidly growing demand for data‑science education and the inadequacy of traditional statistics curricula to meet the practical needs of learners. While many recent opinion pieces call for more computing in statistics programs, the authors argue that the primary priority should be to place real‑world applications at the heart of instruction, echoing Nolan and Speed’s (1999) call for an “application‑first” approach. They further contend that instructors who design and teach data‑science courses must possess not only solid statistical training but also hands‑on experience solving authentic problems with data.

Drawing on their experience developing a graduate‑level introductory data‑science course built entirely around case studies, the authors present a set of guiding principles and a detailed implementation roadmap. The course is organized around three core competencies they label “creating, connecting, and computing.” “Creating” refers to the ability to formulate new analytical questions and design end‑to‑end data pipelines; “connecting” denotes the skill of integrating statistical theory with domain knowledge to generate actionable insights; and “computing” emphasizes reproducible coding, version control, and efficient workflow automation using both R and Python.

The curriculum is divided into three sequential modules: (1) data exploration and preprocessing, (2) statistical modeling and machine‑learning techniques, and (3) interpretation, communication, and decision‑making. Each module is anchored by a real‑world data set drawn from diverse domains such as healthcare, finance, environmental science, and social media. Students work in small teams to define problems, acquire and clean data, apply appropriate analytical methods, evaluate model performance, and present findings in written reports and oral presentations.

Assessment departs from traditional exams and relies on project‑based deliverables. Grading criteria include clarity of problem definition, adequacy of data preparation, methodological soundness, depth of interpretation, and effectiveness of communication. This approach treats the analytical process itself as the learning outcome, reinforcing the three competencies throughout the semester.

A pilot run of the course with thirty graduate students demonstrated high satisfaction and measurable skill gains. Participants reported increased confidence in data wrangling, stronger ability to apply statistical reasoning to real problems, and improved collaborative and presentation skills. The final portfolios were cited as valuable assets for job‑market positioning.

In conclusion, the authors provide actionable recommendations for statistics departments seeking to become hubs of data‑science education: (1) define learning objectives that combine statistical thinking with applied problem solving; (2) structure curricula around authentic case studies; (3) ensure instructors have both theoretical expertise and practical data‑analysis experience; (4) embed modern computing tools and reproducibility practices throughout the course; and (5) adopt project‑based assessment to evaluate the full analytical workflow. By following these guidelines, statisticians can effectively bridge the gap between theory and practice and prepare students for the interdisciplinary demands of modern data science.