Skip to main content

Some Criteria for Variable Selection in Factor Analysis

Abstract

Four criteria are proposed for variable selection in factor analysis. Three are introduced from the viewpoint to make the configurations of the true factor scores F and the estimated factor scores F(m) as close as possible. The remaining one comes from the maximization of the variance-covariance matrix due to regression of F on the variables X(m). The relationship among the four criteria and the generalized coefficient of determination (GCD) proposed by Yanai (1980) is discussed. The performances are investigated through the analyses of two sets of real data. As variable selection procedures we propose the forward selection procedure as well as the backward elimination procedure.

This is a preview of subscription content, access via your institution.

References

  • Beale, E.M.L., Kendall, M.G. and Mann, D.W., The discarding of variables in multivariate analysis, Biometrika 54. (1967). 357–366.

    MathSciNet  Article  Google Scholar 

  • Escoufier, Y., Le traitement des variables vectorielles, Biometrics 29 (1973). 751–760.

    MathSciNet  Article  Google Scholar 

  • Escoufier, Y., Robert, P. and Cambon, J. (1974). Construction of a vector equivalent to a given vector from the point of view of the analysis of principal components, COMPSTAT 1974, 155–164.

    MathSciNet  Google Scholar 

  • Escoufier, Y. and Robert, P., (1979). Choosing variable and metrics by optimizing the RV- coefficient, in “Optimizing Methods in Statistics” (ed. Rustagi, J.S.). Academic Press, 1979.

  • Jolliffe, I.T., (1972). Discarding variables in a principal component analysis I. Artificial data, Appl. Statist. 21, 160–173.

    MathSciNet  Article  Google Scholar 

  • Jolliffe, I.T., (1973). Discarding variables in a principal component analysis II. Real data, Appl. Statist. 22, 21–31.

    MathSciNet  Article  Google Scholar 

  • Sano, K. et al., (1977) Statistical studies on evaluation of mild disturbance of consciousness - Abstraction of characteristic clinical pictures by cross-sectional investigation, Shinkei Kenkyu no Shinpo 21, 1052–1065 (in Japanese).

    Google Scholar 

  • Tanaka, Y. and Kodake, K., (1931). A method of variable selection in factor analysis and its numerical investigation, Behaviormetrika 10 49–61.

    Google Scholar 

  • Tanaka, Y., and Kodake, K., (1981). Variable selection in factor analysis — a backward elimination procedure and its computer program, Rep. Research and Development, Okayama University Computer Center, Vol. I,No. 5, 1–34.

    Google Scholar 

  • Tanaka, Y., (1981). Variable selection in factor analysis, Preprint of Symposium on “Variable selection, missing value and the related topics” at Hiroshima University, Dec. 10–12, (in Japanese).

    Google Scholar 

  • Tanaka, Y., Kodake, K. and Seo, H., (1982). An improved version of variable selection in factor analysis — a backward elimination and a forward selection procedures and their programs, Rep. Research and Development, Okayama University Computer Center (in press).

    Google Scholar 

  • Yanai, H., (1980). A proposition of generalized method for forward selection of variables, Behaviormetrika, 7, 95–107.

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

About this article

Cite this article

Tanaka, Y. Some Criteria for Variable Selection in Factor Analysis. Behaviormetrika 10, 31–45 (1983). https://doi.org/10.2333/bhmk.10.13_31

Download citation

  • Received:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.2333/bhmk.10.13_31

Key Words and Phrases

  • variable selection
  • factor analysis
  • configuration of factor scores
  • forward selection
  • backward elimination