Abstract:
Mathematical knowledge is essential to improve the
analytical thinking of engineering undergraduates. Exploring
more information from existing academic data is an essential
aspect of the educational research. The objective of this study is
to explore the impact of mathematics performance on different
engineering programs. The study was conducted with 626
engineering students from seven different disciplines at the
Faculty of Engineering, University of Moratuwa, Sri Lanka.
Canonical Correlation Analysis (CCA) was employed to
investigate the relationship between mathematics courses and
other engineering courses with respect to their disciplines.
Results of CCA revealed that the mathematics performance in
both semester 1 and 2 influences significantly on the students’
academic performance in Level 2 of the seven engineering
disciplines considered. Wilk’s lambda test statistic confirmed that
only the first canonical variate pair is significant for all
disciplines. The squared canonical correlations of first canonical
variate pair indicated that the amount of variance between the
mathematics performance and academic performance in Level 2
explained varied among seven disciplines from 42% to 68%. The
impact is higher from mathematics in semester 2 than that from
semester 1 in all disciplines except for Material Science and
Engineering discipline. The explainable variability of student
academic performance in Level 2 by the canonical variate of
mathematics is varied from 27% to 50% among seven disciplines.
Based on preliminary analysis, it can be concluded that the
performance in mathematics in Level 1 could indicate the trend
towards the student academic performance in all engineering
programs.
Citation:
K. A. D. S. A. Nanayakkara and T. S. G. Peiris, "Application of Canonical Correlation Analysis to study the influence of mathematics on engineering programs: A case study," 2016 Moratuwa Engineering Research Conference (MERCon), 2016, pp. 137-141, doi: 10.1109/MERCon.2016.7480129.