The present paper reports on a "Monte Carlo" comparison of two methods of testing the significance of a correlation matrix to determine the suitability and appropriateness of factor analysis. Bartlett's (1950) chi-square test of sphericity and Steiger's (1980) chi-square test are evaluated using 320 computer-generated correlation matrices from samples of N = 20 and N = 200, having actual population correlation coefficients ranging from .01 to .64. A recommendation is made to use Steiger's test prior to factor analysis due to its increased power and computational simplicity relative to Bartlett's test.
Get full access to this article
View all access options for this article.
References
1.
Armstrong, J. C.Derivation of theory by means of factor analysis or Tom Swift and his electric factor analysis machine . American Statistician, 1967, Dec., 17-21.
2.
Armstrong, J. C. and Soelberg, P.On the interpretation of factor analysis. Psychological Bulletin, 1968, 70, 361-364.
3.
Bartlett, M. S.Tests of significance in factor analysis . British Journal of Psychology, 1950, 3, 77-85.
4.
Box, G. E. P. and Muller, M.A note on the generation of random normal deviates. Annals of Mathematical Statistics, 1958, 29, 610.
5.
Dziuban, C. D. and Harris, C. W.On the extraction of components and the applicability of the factor model. American Educational Research Journal, 1973, 10, 93-99.
6.
Dziuban, C. D. and Shirkey, E. C.When is a correlation matrix suitable for factor analysis? Some decision rules. Psychological Bulletin, 1974, 81, 358-361.
7.
Fisher, R. A.On the probable error of a coefficient of correlation deduced from a small sample . Metron, 1921, 1, 1-32.
8.
Knapp, T. R. and Swoyer, V. H.Some empirical results concerning the power of Bartlett's test of the significance of a correlation matrix. American Educational Research Journal, 1967, 4, 13-17.
9.
Maxwell, A. E.Statistical methods in factor analysis . Psychological Bulletin, 1959, 56, 228-235.
10.
Steiger, J. H.Tests for comparing elements of a correlation matrix : Psychological Bulletin, 1980, 87, 245-251.
