![](bg8.png)
7 CONCLUSIONS
This study analyzed the association between how stu-
dents evaluate a course and how students evaluate a
teacher using canonical correlation analysis (CCA).
Data from student evaluations is characterized by high
correlations between the variables within each set of
variables, therefore two modifications of the CCA
method; regularized CCA and sparse CCA, together
with classical CCA were applied to find the most
interpretable model of association between the two
evaluations.
The association between how students evaluate
the course and how students evaluate the teacher was
found to be quite strong in all three cases. How-
ever, applications of regularized and sparse CCA to
the present student evaluation data give results with
increased interpretability over traditional CCA.
The simplest model was obtained from sparse
canonical correlation analysis, where an association
between how students evaluate the course and how
students evaluate the teacher was found to be due to
the relationship between the good continuity between
teaching activities in the course, the content of the
course, the teaching material, and the overall qual-
ity of the course from the course side; and teachers
ability to give a good grasp of the academic content
of the course, the teachers ability to motivate the stu-
dents and the teachers good communication about the
subject on the teacher side.
Analysis of subsequent evaluations of the same
course showed that the association between how stu-
dents rate the teacher and the course was found to be
subject to subtle changes with the change of teach-
ing methods and with the change of instructor. These
changes in the correlation structure were seen on the
instructor side and not on the course side.
REFERENCES
Abrami, P. C., d’Apollonia, S., and Rosenfield, S. (1997).
The dimensionality of student ratings of instruction:
what we know and what we do not. Perry, R.P., Smart
J.C., editors: effective teaching in higher education:
research and practice. New York: Agathon Press.
Cohen, P. A. (1981). Student rating of instruction and stu-
dent achievement. Review of Educational Research,
51(3):281–309.
D
´
ejean, S. and Gonz
´
alez, I. (2009). Package ”CCA: Canon-
ical correlation analysis”. CRAN.
Feldman, K. A. (1989). The association between student
ratings of specific instructional dimensions and stu-
dent achievement: Refining and extending the syn-
thesis of data from multisection validity studies. Re-
search in Higher education, 30(6).
Gonz
´
alez, I., D
´
ejean, S., Martin, P. G. P., and Baccini,
A. (2009). Highlighting relationships between het-
erogeneous biological data through graphical displays
based on regularized canonical correlation analysis.
Journal of Biological Systems, 17(2):173–199.
Hardoon, D. R. and Shawe-Taylor, J. (2011). Sparse
canonical correlation analysis. Machine Learning,
83(3):331–353.
Hoerl, A. and R.W., K. (1970). Ridge regression: Biased es-
timation for nonorthogonal problems. Technometrics,
12:55–67.
Hotelling, H. (1935). The most predictable criterion. Jour-
nal of Educational Psychology, 26:139–142.
Le Cao, K.-A., Martin, P. G. P., Christele, R., and Besse,
P. (2009). Sparse canonical methods for biological
data integration: application to a cross-platform study.
BMC Bioinformatics, 10:Article 34.
Leurgans, S., Moyeed, R., and Silverman, B. (1993).
Canonical correlation analysis when the data are
curves. Journal of the Royal Statistical Society B,
55(3):725–740.
Likert, R. (1932). A technique for the measurement of atti-
tudes. Archives of Psychology, 140:155.
Marsh, H. W. (1987). Students’ evaluations of university
teaching: Research findings, methodological issues,
and directions for future research. International Jour-
nal of Educational Research, 11(3):253 – 388.
Marsh, H. W. (2007). Students evaluations of university
teaching: Dimensionality, reliability, validity, poten-
tial biases and usefulness. R.P. Perry and J.C. Smart
(eds.), The Scholarship of Teaching and Learning in
Higher Education: An Evidence-Based Perspective,
pages 319 –383.
Marsh, H. W. and Roche, L. A. (1997). Making students’
evaluations of teaching effectiveness effective: The
critical issues of validity, bias, and utility. American
Psychologist, 52(11):1187.
Parkhomenko, E., Tritchler, D., and Beyene, J. (2007).
Genome-wide sparse canonical correlation of gene ex-
pression with genotypes. BMC Proceedings, 1.
Vinod, H. D. (1976). Canonical ridge and econometrics of
joint production. Journal of Econometrics, 4(2):147–
166.
Waaijenborg, S. and Zwinderman, A. (2007). Penalized
canonical correlation analysis to quantify the associa-
tion between gene expression and dna markers. BMC
Proceedings, 1(Suppl 1):S122.
Witten, D. M., Tibshirani, R., and Gross, S. (2013). Package
”PMA”: Penalized multivariate analysis.
Witten, D. M., Tibshirani, R., and Hastie, T. (2009). A
penalized matrix decomposition, with applications to
sparse principal components and canonical correlation
analysis. Biostat, 10(3):515–534.
Zou, H. and Hastie, T. (2005). Regularization and variable
selection via the elastic net. Journal of the Royal Sta-
tistical Society, Series B, 67:301320.
HowdoStudentEvaluationsofCoursesandofInstructorsRelate?
287