A statistical study of concept mapping metrics

This paper reports on our exploratory statistical study of the relationships among a selection of traditional and holistic concept mapping metrics. Specifically, twelve traditional metrics (nine from the literature and three of our own design) and four holistic metrics (all from the literature) were used to evaluate the concept maps of two sets of engineering students: (i) 73 undergraduate engineers enrolled in first-year engineering design; and (ii) 52 graduate engineers enrolled in a master's level systems engineering course. Our results showed 41 common correlated pairs between these two samples, all at the p<0.05 level of significance. The implications of these correlations for engineering educators are discussed, along with potential directions for future research to expand this area of study.