Psychometrika

, Volume 32, Issue 4, pp 443–482 | Cite as

Some contributions to maximum likelihood factor analysis

  • K. G. Jöreskog
Article

Abstract

A new computational method for the maximum likelihood solution in factor analysis is presented. This method takes into account the fact that the likelihood function may not have a maximum in a point of the parameter space where all unique variances are positive. Instead, the maximum may be attained on the boundary of the parameter space where one or more of the unique variances are zero. It is demonstrated that suchimproper (Heywood) solutions occur more often than is usually expected. A general procedure to deal with such improper solutions is proposed. The proposed methods are illustrated using two small sets of empirical data, and results obtained from the analyses of many other sets of data are reported. These analyses verify that the new computational method converges rapidly and that the maximum likelihood solution can be determined very accurately. A by-product obtained by the method is a large sample estimate of the variance-covariance matrix of the estimated unique variances. This can be used to set up approximate confidence intervals for communalities and unique variances.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Aitchison, J. & Silvey, S. D. Maximum likelihood estimation procedures and associated tests of significance.Journal of the Royal Statistical Society, Series B, 1960,22, 154–171.Google Scholar
  2. Anderson, T. W.An introduction to multivariate statistical analysis. New York: Wiley, 1958.Google Scholar
  3. Bargmann, R. A study of independence and dependence in multivariate normal analysis. University of North Carolina, Institute of Statistics Mimeo Series No. 186, 1957.Google Scholar
  4. Bechtoldt, H. P. An empirical study of the factor analysis stability hypothesis.Psychometrika, 1961,26, 405–432.Google Scholar
  5. Bellman, R.Introduction to matrix analysis. New York: McGraw-Hill, 1960.Google Scholar
  6. Box, G. E. P. A general distribution theory for a class of likelihood criteria.Biometrika, 1949,36, 317–346.Google Scholar
  7. Browne, M. W. A comparison of factor analytic techniques. Master's Thesis, University of Witwatersrand, South Africa, 1965.Google Scholar
  8. Davis, F. B. Fundamental factors of comprehension in reading.Psychometrika, 1944,9, 185–197.Google Scholar
  9. Emmett, W. G. Factor analysis by Lawley's method of maximum likelihood.British Journal of Psychology, Statistical Section, 1949,2, 90–97.Google Scholar
  10. Fletcher, R. & Powell, M. J. D. A rapidly convergent descent method for minimization.Computer Journal, 1963,2, 163–168.Google Scholar
  11. Harman, H. H.Modern factor analysis. Chicago: University of Chicago Press, 1960.Google Scholar
  12. Hemmerle, W. J. Obtaining maximum-likelihood estimates of factor loadings and communalities using an easily implemented iterative procedure.Psychometrika, 1965,30, 291–302.Google Scholar
  13. Howe, W. G. Some contributions to factor analysis. Report No. ORNL-1919, Oak Ridge National Laboratory, Oak Ridge, Tennessee, 1955.Google Scholar
  14. Jöreskog, K. G.Statistical estimation in factor analysis. Stockholm: Almqvist & Wiksell, 1963.Google Scholar
  15. Jöreslkog, K. G. Testing a simple structure hypothesis in factor analysis.Psychometrika, 1966,31, 165–178.Google Scholar
  16. Jöreskog, K. G. UMLFA-a computer program for unrestricted maximum likelihood factor analysis. Research Memorandum 66-20. Princeton, New Jersey: Educational Testing Service. Revised Edition 1967.Google Scholar
  17. Kendall, M. G. & Stuart, A.The advanced theory of statistics, Volume 2. London: Charles Griffin and Co., 1961.Google Scholar
  18. Lawley, D. N. The estimation of factor loadings by the method of maximum likelihood.Proceedings of the Royal Society of Edinburgh, Section A, 1940,60, 64–82.Google Scholar
  19. Lawley, D. N. Further investigations in factor estimation.Proceedings of the Royal Society of Edinburgh, Section A, 1942,61, 176–185.Google Scholar
  20. Lawley, D. N. The application of the maximum likelihood method to factor analysis.British Journal of Psychology, 1943,33, 172–175.Google Scholar
  21. Lawley, D. N. A statistical examination of the centroid method.Proceedings of the Royal Society of Edinburgh, Section A, 1955,64, 175–189.Google Scholar
  22. Lawley, D. N. Some new results in maximum likelihood factor analysis.Proceedings of the Royal Society of Edinburgh, Section A, 1967,67, 256–264.Google Scholar
  23. Lawley, D. N. & Maxwell, A. E.Factor analysis as a statistical method. London: Butterworths, 1963.Google Scholar
  24. Lord, F. M. A study of speed factors in tests and academic grades.Psychometrika, 1956,21, 31–50.Google Scholar
  25. Mattsson, A., Olsson, U., & Rosen, M. The maximum likelihood method in factor analysis with special consideration to the problem of improper solutions. Research Report, Institute of Statistics, University of Uppsala, Sweden, 1966.Google Scholar
  26. Maxwell, E. A. Recent trends in factor analysis.Journal of the Royal Statistical Society, Series A, 1961,124, 49–59.Google Scholar
  27. Neyman, J. & Pearson, E. S. On the use and interpretation of certain test criteria for purposes of statistical inference.Biometrika, 1928,20A, 175–240, 263–294.Google Scholar
  28. Ortega, J. M. On sturm-sequences for tri-diagonal matrices.Journal of the Association of Computing Machinery, 1960,7, 260–263.Google Scholar
  29. Ortega, J. M. & Kaiser, H. F. The LLT and QR methods for symmetric tri-diagonal matrices.Computer Journal, 1963,6, 99–101.Google Scholar
  30. Rao, C. R. Estimation and tests of significance in factor analysis.Psychometrika, 1955,20, 93–111.Google Scholar
  31. Rippe, D. D. Application of a large sampling criterion to some sampling problems in factor analysis.Psychometrika, 1953,18, 191–205.Google Scholar
  32. Wilkinson, J. H. The calculation of eigenvectors of codiagonal matrices.Computer Journal, 1958,1, 90–96.Google Scholar
  33. Wilkinson, J. H. Householder's method for the solution of the algebraic eigenproblem.Computer Journal, 1960,3, 23–27.Google Scholar
  34. Wilks, S. S. The large-sample distribution of the likelihood ratio for testing composite hypotheses.Annals of Mathematical Statistics, 1938,9, 60–62.Google Scholar

Copyright information

© Psychometric Society 1967

Authors and Affiliations

  • K. G. Jöreskog
    • 1
  1. 1.Educational Testing ServiceUSA

Personalised recommendations