Author(s):
As big data becomes ubiquitous in every aspect of our day-to-day lives, it is increasingly vital for students to develop data literacy skills and learn how to make sense of and draw conclusions from large and complex datasets. One opportunity to foster these skills is DataFest, a collaborative data competition sponsored by the American Statistical Association that serves over 2000 students at over 100 universities across the globe. During DataFest, teams of students have 48 hours to explore an authentic dataset provided by a community partner and to answer a real-world question that arises from that dataset. Because DataFest is a potentially impactful event at which students can develop key skills (e.g., communication, data literacy, interdisciplinary reasoning) and gain access to professional development opportunities, it is vital to ensure that DataFest serves all students. In this lightning talk, we will report findings from 2 years of mixed-methods data collection across 6 sites exploring the question, “Who participates in DataFest and why?” Qualitative and quantitative findings reveal how factors such as the extent to which DataFest is perceived as welcoming, for “me”, and the relevance of previous years’ topics to students’ lives impact whether or not students decide to participate in DataFest. Additionally, the talk will touch on some of the methodological challenges our team faced, including collecting data remotely from multiple institutions and collecting data from different groups of stakeholders, including non-DataFest participants.
