RUME 28
2026
Alexandria, Virginia
Integrating Computational Thinking in Undergraduate Statistics Projects: A Comparative Analysis
Page: 1462
We conducted a pilot study that explored the integration of computational thinking (CT) in the teaching and learning of statistics. Participants were undergraduate college students enrolled in an elementary statistics course addressed to students with various majors (Group 1), and in a mathematics course addressed to future early childhood and elementary education teachers (Group 2). The statistics curriculum for Group 2 students included only descriptive statistics. Both groups of students completed a project containing the following: title and research question, data collection/ dataset description, descriptive statistics and/or inferential statistics, visual representations, analysis and interpretation, CT reflection, references, data source documentation. Data was analyzed across the CT core components: i) decomposition- dividing problems into manageable parts; ii) pattern recognition – identifying patterns, trends, correlations; iii) abstraction – simplifying the problem, focusing on essential variables or characteristics; iv) algorithm design – constructing an algorithm or a sequence of computational steps. Both groups scored high on decomposition. Some of the projects from Group 2 demonstrated strong pattern recognition. The projects from Group 1 achieved higher scores in abstraction and algorithm design. Overall, Group 1 reflections showed stronger CT integration. The CT integration in statistics is promising, but we need to account for its variability across educational contexts, including learners and curricula.