The present study considers the problem of multidimensionality in Tertiary Entrance (TE) scores where a single TE score is the desired goal. Using data from the 1988 cohort of the ACT college system, course scores as assessed by teachers were shown to distinguish performance in a four-dimensional space. TE scores, computed using both a modified multiple regression strategy and the Daley's (1989) Other Course Score scaling method, were shown to be related to, at best, two of the four dimensions. A second phase of the study revealed the presence of multidimensionality in the choices of courses that students made when assembling their college curricula. These dimensions of course choice were subsequently related back to the demographic characteristics of the students and to the two types of TE scores. Conclusions were drawn regarding the dubious validity of assuming that a single TE score carries all the information needed to summarise the performance of secondary school students.
AnderbergM. (1973). Cluster analysis for applications. New York: Academic Press.
3.
Committee for the Review of Tertiary Entrance Score Calculations in the ACT (B. McGaw, Chair). (1986). Making admission to higher education fairer: Report. Canberra: ACT Schools Authority, Australian National University, & Canberra College of Advanced Education.
4.
CookseyR.W. (1982). A modified version of the ISODATA program. Unpublished manuscript, Department of Psychology, University of New England, Armidale, New South Wales.
5.
CookseyR.W. (1989). Exploring the existence of bias in tertiary entrance scores: Definitions, measurement, and control procedures. Final report to the ACT Schools Authority, Canberra.
6.
CoxonA. (1982). The user's guide to multidimensional scaling. London: Heinemann Educational Books.
7.
DaleyD. (1988). Scaling procedures for constructing fair tertiary entrance admission indices, with special reference to the Australian Capital Territory tertiary entrance score: Interim report to the ACT Schools Authority, Canberra.
8.
DaleyD. (1989). Determining relative academic achievement for fair admission to higher education. Report to a Joint Committee of the Australian National University, Canberra College of Advanced Education, and the ACT Schools Authority, Canberra.
9.
DavisonM. (1983). Multidimensional scaling. New York: John Wiley & Sons.
10.
EdwardsR.A. (1990). An examination of procedures for generating tertiary entrance scores in the ACT. Interim Report, Accreditation Section, ACT Department of Education, Canberra.
11.
HallD. & KhannaD. (1977). The ISODATA method computation for the relative perception of similarities and differences in complex and real data. In EnsteinK.RalstonA., & WilfH. (Eds.), Statistical methods for digital computers (Vol. 3, pp. 340–373). New York: John Wiley & Sons.
LathropR.G. & WilliamsJ.E. (1987). The reliability of inverse scree tests for cluster analysis. Educational and Psychological Measurement, 47, 953–959.
14.
LorrM. (1983). Cluster analysis for social scientists. San Francisco: Jossey-Bass.
15.
MastersG. (1988). Anchor tests, score equating, and sex bias. Australian Journal of Education, 32, 25–43.
16.
MastersG. & BeswickD. (1986). The construction of tertiary entrance scores: Principles and issues. Melbourne: University of Melbourne, Centre for the Study of Higher Education.
17.
McDonaldR. (1985). Factor analysis and related methods. Hillsdale, NJ: Lawrence Erlbaum Associates.
18.
MorganG. & McGawB. (1988). Proposed combinations of ASAT subscores for scaling course scores in the ACT. Preliminary Report. Hawthorn, Vic.: ACER.
19.
SchiffmanS.ReynoldsM., & YoungF. (1981). Introduction to multidimensional scaling: Theory, methods, and applications. New York: Academic Press.
20.
SokalR. & SneathP. (1973). Numerical taxonomy. San Francisco: W.H. Freeman.
