Skip to main content
SpringerLink
Log in

An EM Algorithm for ML Factor Analysis with Missing Data

  • Conference paper
Latent Variable Modeling and Applications to Causality

Part of the book series: Lecture Notes in Statistics ((LNS,volume 120))

Abstract

EM algorithm is a popular algorithm for obtaining maximum likelihood estimates. Here we propose an EM algorithm for the factor analysis model. This algorithm extends a previously proposed EM algorithm to handle problems with missing data. It is simple to implement and is the most storage efficient among its competitors. We apply our algorithm to three examples and discuss the results. For problems with reasonable amount of missing data, it converges in reasonable time. For problems with large amount of missing data EM algorithm is usually slow. For such cases we successfully apply two EM acceleration methods to our examples. Finally, we discuss different methods of obtaining standard errors and in particular we recommend a method based on center difference approximation to the derivative.

A major part of this research was done when the author was an assistant Professor at at Isfahan University of Technology

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 84.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Allison, P. D. (1987). Estimation of linear models with incomplete data. In C. Clogg (Ed.)Sociological Methodology(pp 71–103). San Francisco: Jossey-Bass.

    Google Scholar 

  2. Arminger, G. & Sobel, M. E. (1990). Pseudo-maximum likelihood estimation of mean and covariance structure with missing data.Journal of the American Statistical Association 85195–203.

    Article  MathSciNet  Google Scholar 

  3. Bentler, P. M. (1992).EQS Structural Equations Program Manual.Los Angeles: BMDP Statistical Software.

    Google Scholar 

  4. Broyden, C. G. (1965). A Class of Methods for Solving Nonlinear Simultaneous Equations.Math. Comp. 19577–593.

    Article  MathSciNet  MATH  Google Scholar 

  5. Dempster, A. P., Laird, N. M., & Rubin, D. B. (1977). Maximum Likelihood from Incomplete Data via the EM Algorithm (with Discussion).Journal of the Royal Statistical Society B391–38.

    MathSciNet  Google Scholar 

  6. Dennis, J. E., & Schnabel, R. B. (1983).Numerical Methods for Unconstrained Optimization and Nonlinear Equations. Englewood Cliffs, New Jersey: Prentice-Hall.

    MATH  Google Scholar 

  7. Efron, B. & Hinkley, D. V. (1978). The observed versus the expected information.Biometrika 65457–487.

    Article  MathSciNet  MATH  Google Scholar 

  8. Finkbeiner, C. (1979). Estimation for the multiple factor model when data are missing.Psychometrika 44409–420.

    Article  MATH  Google Scholar 

  9. Fisher, R. A. (1925). Theory of Statistical Estimation.Proceedings of Cambridge Philosophical Society 22700–725.

    Article  MATH  Google Scholar 

  10. Gruvaeus, G. T. & Jöreskog, K. G. (1970).A computer program for minimizing a function of several variables(E.T.S. Res. Bull. RB770–14). PrinceFraton, N. J.:Educational Testing Service.

    Google Scholar 

  11. Holzinger, K. J. & Swineford, F. (1939). A study in factor analysis: The stability of a bi-factor solution.Supplementary Educational MonographNo. 48. Chicago: University of Chicago.

    Google Scholar 

  12. Jamshidian, M. (1988).Application of the Conjugate Gradient Methods in Statistical ComputingUniversity of California, Los Angeles, Ph.D. Thesis.

    Google Scholar 

  13. Jamshidian, M. & Bentler, P. M. (1994). Using complete data routines for ML estimation of mean and covariance structures with missing data, submitted.

    Google Scholar 

  14. Jamshidian, M. & Jennrich, R. I. (1994a). Conjugate Gradient Methods in Confirmatory Factor Analysis.Computational Statistics and Data Analysis 17247–263.

    Article  MATH  Google Scholar 

  15. Jamshidian, M. & Jennrich, R. I. (1994b). Quasi Newton acceleration of the EM algorithm, submitted.

    Google Scholar 

  16. Jamshidian, M., & Jennrich, R. I. (1994c), Computing the observed information matrix using numerical differentiationmanuscript under preparation.

    Google Scholar 

  17. Jamshidian, M., & Jennrich, R. I. (1993). Conjugate Gradient Acceleration of the EM Algorithm.Journal of theAmericanStatistical Association 88221–228.

    Article  MathSciNet  MATH  Google Scholar 

  18. Jöreskog, K. G. & Sörbom, D. (1988).LISREL 7 A guide to the program and applications.SPSS, Chicago.

    Google Scholar 

  19. Khalfan, H. F., Byrd, R. H., & Schnabel, R. B. (1993). A Theoretical and Experimental Study of the Symmetric Rank-One Update.SIAM Journal on Optimization 31–24.

    Article  MathSciNet  MATH  Google Scholar 

  20. Lee, S. Y. (1986). Estimation for structural equation models with missing data.Psychometrika 5193–99.

    Article  MathSciNet  MATH  Google Scholar 

  21. Little, R. J. A. & Rubin, D. B. (1987).Statistical analysis with missing data.New York: Wiley.

    MATH  Google Scholar 

  22. Louis, T. A. (1982). Finding the Observed Information Matrix When Using the EM Algorithm.Journal of the Royal Statistical Society Ser. B, 44226–233.

    MathSciNet  MATH  Google Scholar 

  23. Meng, X. L. & Rubin, D. B. (1991). Using EM to Obtain Asymptotic Variance-Covariance Matrices: the SEM Algorithm.Journal of the American Statistical Association 86899–909.

    Article  Google Scholar 

  24. Muthen, B., Kaplan, D., & Hollis, M. (1987). On structural equation modeling with data that are not missing completely at random.Psychornetrika 52 431–462.

    Article  MATH  Google Scholar 

  25. Rubin, B. & Thayer, D. T. (1982). EM algorithm for ML factor analysis.Peychometrika 4769–76.

    Article  MathSciNet  MATH  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. BMDP Statistical Software, Isfahan, Iran

    Mortaza Jamshidian

Authors
  1. Mortaza Jamshidian
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Department of Mathematics, Harvard University, Cambridge, MA, 02138, USA

    Maia Berkane

Rights and permissions

Reprints and permissions

Copyright information

© 1997 Springer-Verlag New York, Inc.

About this paper

Cite this paper

Jamshidian, M. (1997). An EM Algorithm for ML Factor Analysis with Missing Data. In: Berkane, M. (eds) Latent Variable Modeling and Applications to Causality. Lecture Notes in Statistics, vol 120. Springer, New York, NY. https://doi.org/10.1007/978-1-4612-1842-5_13

Download citation

  • DOI: https://doi.org/10.1007/978-1-4612-1842-5_13

  • Publisher Name: Springer, New York, NY

  • Print ISBN: 978-0-387-94917-8

  • Online ISBN: 978-1-4612-1842-5

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation