Students’ Articulation of Uncertainty About Big Data in IMA Learning Environment

Abstract

This study examines students’ expressions of uncertainty while interacting with classic and nontraditional big data analyses. The study was designed according to the integrated modeling approach (IMA), which was found to be suitable for the development of reasoning with uncertainty in a classic data setting. Over the course of the activity, 87 expressions of uncertainty were identified. A total of ten types of uncertainty expressions were identified: eight occurred during big data activities, and five occurred during classic data activities. Furthermore, a conceptual framework for describing novices’ reasoning with uncertainty with big data has been developed. The study also illustrates the pedagogical potential of implementing IMA in big data settings and combining classic data with big data investigations.