This short report gives an update on the NSF-supported project “ERI: Towards Data-Capable Engineers with a Variability-Capable Mindset” (Grant No. 2138463).
Statistical variability is important, but under-emphasized in engineering. Variability is the phenomenon of non-identical behavior, which has important effects on designing systems for people (who are different), and on designing for safety (in the face of variable conditions). Our project seeks to better understand how people—engineers in particular—react to statistical variability, and to use these insights to improve undergraduate education.
Statistical variability is under-emphasized in engineering: A recent review of the education literature on mathematical practices in engineering found that only 2 out of 5,466 even discuss "uncertainty" or "error" [1]. Our scoping review of textbooks actively used to teach engineering courses found that only 11% of textbooks mentioned "variability" [2]. Despite this neglect, variability remains important to engineering practice; for example, female automobile passengers in the U.S. experience 47% higher odds of injury than males [3], a disparity that the Government Accountability Office attributes to poor statistical modeling practices in crash testing [4].
This report focuses on results from the final (quantitative) phase of our project: The development of a survey instrument to measure decision-making under variability, and the deployment of the instrument with a large and representative sample. Our results have implications for education theorists seeking to better understand statistical thinking, and for engineering educators seeking to promote statistical thinking in their own classes.
References
[1] K. Hadley and W. Oyetunji, “Extending the Theoretical Framework of Numeracy to Engineers,” J. Eng. Educ., vol. 111, no. 2, pp. 376–399, Apr. 2022, doi: 10.1002/jee.20453.
[2] K. Vo, A. Evans, S. Madan, and Z. del Rosario, “A Scoping Review of Engineering Textbooks to Quantify the Teaching of Uncertainty,” in ASEE Annual Conference and Exposition, 2023.
[3] D. Bose, M. Segui-Gomez, ScD, and J. R. Crandall, “Vulnerability of Female Drivers Involved in Motor Vehicle Crashes: An Analysis of US Population at Risk,” Am. J. Public Health, vol. 101, no. 12, pp. 2368–2373, Dec. 2011, doi: 10.2105/AJPH.2011.300275.
[4] GAO, “Vehicle Safety: DOT Should Take Additional Actions to Improve the Information Obtained from Crash Test Dummies,” U.S. Government Accountability Office, GAO-23-105595, Mar. 2023. Accessed: Mar. 13, 2023. [Online]. Available: https://www.gao.gov/products/gao-23-105595
The full paper will be available to logged in and registered conference attendees once the conference starts on June 22, 2025, and to all visitors after the conference ends on June 25, 2025