This session opens the event and sets the stage for the program ahead. Key topics include introductory comments, an overview of the event’s objectives, and acknowledgments of participants and sponsors.

Data visualisation is an important tool for identifying patterns in data and communicating findings effectively. This session will cover the reasons for visualising data, provide guidelines for creating more effective charts, and discuss examples of good and poor visualisations.

Scrollytelling is a powerful but often inaccessible method for presenting data-driven stories due to technical barriers. This session covers the motivations behind the design of Closeread, details from the first Posit scrollytelling contest, and upcoming features such as scrolling video support and improved integration with R and Python.

Generative AI tools have brought to light pre-existing weaknesses in data science education’s learning design and assessment. Consequently, the session will explore how “learning to learn” can be re-evaluated, how assessment can be reframed as an evidence-gathering process, and how learning experiences can be designed to foster self-regulated learning skills and normalise authentic learning alongside Generative AI.

Our wombats are digging up a description still…

Preferential datasets, often structured as rankings across multiple columns or rows, can be cumbersome to work with. The prefio R package will be introduced, demonstrating a tidy method for managing preferences and providing convenient operations for manipulating preferential data, and an interactive component will also be included.

Existing data visualisations of uncertainty are not effective at preventing false conclusions, despite their utility in understanding data variability. A new ggplot extension, ggdibbler, is introduced to facilitate uncertainty visualisation for preventing false signals, and its seamless integration into existing workflows alongside its alternative visualisations are illustrated.

This session, featuring Professor Rob Hyndman and Dr. Nick Tierney, aims to clarify concepts and demonstrate the impact of software on data analysis. The meanings of research software engineering, open source software, and reproducibility research will be explored, alongside the specific considerations for creating statistical software and R packages, and the contributions of software design and open source packages to the development, dissemination, and accessibility of data-driven analysis will be highlighted.

While research code offers flexibility compared to point-and-click statistical software, it is more susceptible to various types of errors and rarely undergoes formal peer review. This session will cover challenges in peer reviewing research code, the structure and aims of a pilot peer code review program within the Australia-Aotearoa Consortium for Epidemic Forecasting Analytics (ACEFA), evaluation of the program’s effectiveness, and promoting code review as a supportive community practice in computational research.

New data teams often struggle to balance stakeholders’ demands for immediate results with the need to invest in long-term capabilities. Key session topics include managing the tension between quick wins and long-term impact, navigating stakeholder expectations, building team credibility, and developing the necessary infrastructure to support evolving policy priorities within government contexts.

The Mayi Kuwayu Study is a significant national longitudinal survey focusing on Aboriginal and Torres Strait Islander culture, health, and wellbeing, for which a data pipeline re-development project was undertaken. Specifically, the study and team context, the development of its data pipeline, the role of people in design decisions, and the use of the development as an opportunity to upskill the team will be discussed.

After a session focused on summarizing the event and reflecting on key discussions, the closing remarks will cover major takeaways, highlight significant achievements, express gratitude to participants and organizers, and outline next steps or future opportunities.