June 15, 2019
June 15, 2019
October 19, 2019
Engineering Design Graphics Division Technical Session 2 - Design & Manufacturing Topics
Engineering Design Graphics
Spatial visualization skills have been long identified as critical competence for success in STEM disciplines, particularly in engineering and technology fields. Several initiatives to improve these skills have been implemented at various academic institutions. This study aims to apply data analytics (DA) to generate a predictive model for improvement of scores in a commonly used spatial visualization test. This model is based on pre- and post- scores by first-year engineering students, and the objective is to identify the factors that have the largest influence on the improvement of the scores. The generated predictive model provides information on dominant factors, i.e., specific questions in the test or demographics, that will help in establishing pedagogical activities aimed at improving spatial skills of students. The dataset used in this study is from a college of engineering’s incoming class, who are required to take the visualization test, and then are offered a one-credit course. Initial analyses are for initial validation of the generated model by comparing the results to previously generated ones. Three different definitions of improvement are used in this study, i.e., raw score, percentage, and tier, given that particular objectives might be different. Results from this study are in line with one observed in previous reports, with an overall test performance improvement, and more involved test question being more influential factors. Similarly, some of the results involving demographic factors follow in a limited fashion previously observed trends. This study shows that DA is a useful tool that will help in the search for specific objective information regarding the value of activities aimed at improving spatial visualization skills.
Rodriguez, J., & Bairaktarova, D. (2019, June), Evaluation of Improvements in Visualization Test Scores Using Predictive Analytics Paper presented at 2019 ASEE Annual Conference & Exposition , Tampa, Florida. 10.18260/1-2--32765
ASEE holds the copyright on this document. It may be read by the public free of charge. Authors may archive their work on personal websites or in institutional repositories with the following citation: © 2019 American Society for Engineering Education. Other scholars may excerpt or quote from these materials with the same citation. When excerpting or quoting from Conference Proceedings, authors should, in addition to noting the ASEE copyright, list all the original authors and their institutions and name the host city of the conference. - Last updated April 1, 2015