The Geometry of Factorial Indeterminancy | Psychometrika | Cambridge Core (original) (raw)

Abstract

The N-dimensional geometry of a Spearman-Thurstone factor solution reveals two sources for the indeterminancy of factor scores: indeterminancy of total factor space and a rotational indeterminancy within a given total factor space. The analytical papers of Ledermann [4] and Guttman [2] on indeterminancy of factor scores are related to these findings and a simple vector model is developed to reveal the properties of rotational indeterminancy. The significance of factor-score indeterminancy is discussed in light of these findings.

References

Guttman, L. General theory and methods of matric factoring. Psychometrika, 1944, 9, 1–16.CrossRefGoogle Scholar

Guttman, L. The determinancy of factor score matrices with implications for five other basic problems of common factor theory. Brit. J. statist. Psychol., 1955, 8, 65–81.CrossRefGoogle Scholar

Harman, H. Modern factor analysis, Chicago: Univ. Chicago Press, 1960.Google Scholar

Ledermann, W. The orthogonal transformation of a factorial matrix into itself. Psychometrika, 1938, 3, 181–187.CrossRefGoogle Scholar

Sommerville, D. M. Y. An introduction to the geometry of N dimensions, New York: Dover Publications, 1958.Google Scholar

Thomson, G. H. The definition and measurement of_g_. J. educ. Psychol., 1935, 26, 241–262.CrossRefGoogle Scholar

Thurstone, L. L. Multiple-factor analysis, Chicago: Univ. Chicago Press, 1947.Google Scholar