Canonical correlation analysis has been increasingly applied to marketing problems. This article presents some suggestions for interpreting canonical correlations, particularly for avoiding overstatement of the shared variation between sets of independent variables and for explicating relationships among variables within each set.
Get full access to this article
View all access options for this article.
References
1.
AndersonT. W.Introduction to Multivariate Statistical Analysis.New York: John Wiley & Sons, 1958.
2.
BartlettM. S. “The Statistical Significance of Canonical Correlations,” Biometrika, 32 (January 1941), 29–38.
3.
BartlettM. S. “Multivariate Analysis,” Journal of the Royal Statistical Society, Supplement, 9 (1947), 176–90.
4.
CooleyWilliam A. and LohnesPaul R.Multivariate Procedures for the Behavioral Sciences.New York: John Wiley & Sons, 1962.
5.
De GrootM. H. and LiE. C. C. “Correlations Between Similar Sets of Measurements,” Biometrics, 22 (December 1966), 781–90.
6.
GowerJ. C. “A Q-technique for the Calculations of Canonical Variates,” Biometrika, 53 (December 1966), 588–90.
7.
GreenPaul E. and TullDonald S.Research for Marketing Decisions, second edition. Englewood Cliffs, N.J.: Prentice-Hall, 1970, Chapter 11.
8.
GulliksonH.Theory of Mental Tests.New York: John Wiley & Sons, 1950.
9.
HorstPaul. “Relations Among M Sets of Measures,” Psychometrika, 26 (June 1961), 129–49.
10.
HortonI. F., RussellJ. S., and MooreA. W. “Multivariate Covariance and Canonical Analysis: A Method of Selecting the Most Effective Discriminators in a Multivariate Situation,” Biometrics, 24 (December 1968), 845–58.
11.
HotellingHarold. “The Most Predictable Criterion,” Journal of Educational Psychology, 26 (February 1935), 139–42.
12.
HotellingHarold. “Relations Between Two Sets of Variates,” Biometrika, 28 (December 1936), 321–77.
13.
KendallMaurice G.A Course in Multivariate Analysis.New York: Hafner, 1957.
14.
KoonsPaul B.Jr. “Canonical Analysis,” in BorkoHarold, ed., Computer Applications in the Behavioral Sciences.Englewood Cliffs, N.J.: Prentice-Hall, 1962, 266–79.
15.
LawleyD. N. “Tests of Significance in Canonical Analysis,” Biometrika, 46 (June 1959), 59–66.
16.
MariottF. H. C. “Tests of Significance in Canonical Analysis,” Biometrika, 39 (May 1952), 58–64.
MillerJohn K. “The Development and Application of Bimultivariate Correlation: A Measure of Statistical Association Between Multivariate Measurement Sets,” unpublished doctoral dissertation, State University of New York at Buffalo, 1969.
19.
MillerJohn K. and FarrS. David. “Bimultivariate Redundancy: A Comprehensive Measure of Interbattery Relationship,” Multivariate Behavioral Research, 6 (July 1971), 313–24.
RaglandRobert E. “On Some Relations Between Canonical Correlation, Multiple Regression, and Factor Analysis,” unpublished doctoral dissertation, University of Oklahoma, 1967.
22.
RoskamE. “A Program for Computing Canonical Correlations on IBM 1620,” Educational and Psychological Measurement, 26 (Spring 1966), 193–8.
23.
RoyS. N.Some Aspects of Multivariate Statistics.New York: John Wiley & Sons, 1957.
24.
RozeboomW. W. “Linear Correlations Between Sets of Variables,” Psychometrika, 30 (March 1965), 57–71.
25.
SrikantanK. S. “Canonical Association Between Nominal Measurements,” Journal of the American Statistical Association, 65 (March 1970), 284–92.
26.
StewartDouglas and LoveWilliam. “A General Canonical Correlation Index,” Psychological Bulletin, 70 (September 1968), 160–3.
27.
VeldmanDonald J.Fortran Programming for the Behavioral Sciences.New York: Holt, Rinehart and Winston, 1967.
