By Alyssa Hu, Neil J. Hatfield, Matthew D. Beckman
Information
Empowering students to produce insight by engaging and working with data requires that we support their building of powerful and productive ways of computational thinking. Through task-based and semi-structured interviews, we investigate the similarities and differences among individuals’ computational thinking as they engage with data (through exploration, analysis, and communication). Using a grounded theory approach, we analyzed interview transcripts from three undergraduate students, three graduate students, and one professional at a R1 institution, who had R programming experience and were majoring in, studying, or working in statistics or data science. Our results describe six reoccurring themes in participants’ actions: thinking through trade-offs, adapting existing code, visualizations, data file format, hierarchical classification of data, and their perceptions of computational thinking. We then propose an initial framework highlighting aspects of computational thinking, working with data, and resources, and we consider implications for research and teaching.