, Volume 60, Issue 4, pp 489–503 | Cite as

Technical aspects of Muthén's liscomp approach to estimation of latent variable relations with a comprehensive measurement model

  • Bengt O. Muthén
  • Albert Satorra


Muthén (1984) formulated a general model and estimation procedure for structural equation modeling with a mixture of dichotomous, ordered categorical, and continuous measures of latent variables. A general three-stage procedure was developed to obtain estimates, standard errors, and a chi-square measure of fit for a given structural model. While the last step uses generalized least-squares estimation to fit a structural model, the first two steps involve the computation of the statistics used in this model fitting. A key component in the procedure was the development of a GLS weight matrix corresponding to the asymptotic covariance matrix of the sample statistics computed in the first two stages. This paper extends the description of the asymptotics involved and shows how the Muthén formulas can be derived. The emphasis is placed on showing the asymptotic normality of the estimates obtained in the first and second stage and the validity of the weight matrix used in the GLS estimation of the third stage.

Key words

structural equation modeling dichotomous measures generalized least-squares estimation asymptotic covariance matrix 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Amemiya, T. (1978). On a two-step estimation of a multivariate logit model.The Journal of Econometrics, 8, 13–21.Google Scholar
  2. Amemiya, T. (1985).Advanced econometrics. Cambridge, MA: Harvard University Press.Google Scholar
  3. Arminger, G., & Küsters, U. (1988). Latent trait models with indicators of mixed measurement level. In R. Langeheine & J. Rost (Eds.),Latent trit and latent class models (pp. 51–73). New York: Plenum.Google Scholar
  4. Arminger, G., & Küsters, U. (1989). Construction principles for latent trait models. In C. Clogg (Ed.),Sociological Methodology (pp. 369–393). Oxford: Basil Blackwell.Google Scholar
  5. Bermann, G. (1993).Estimation and inference in bivariate and multivariate ordinal probit models. Stocholm, Sweden: Almqvist & Wiksell. (Doctoral dissertation, University of Uppsala, Sweden).Google Scholar
  6. Christoffersson, A. (1975). Factor analysis of dichotomized variables.Psychometrika, 40, 5–32.Google Scholar
  7. Christoffersson, A., & Gunsjö, A. (1983).Analysis of covariance structures for ordinal data (Research Report 83-2). Uppsala, Sweden: University of Uppsala, Department of Statistics.Google Scholar
  8. Gong, G., & Samaniego, F. J. (1981). Pseudo maximum likelihood estimation: Theory and applications.Annals of Statistics, 9, 861–869.Google Scholar
  9. Gourieroux, C., & Montfort, A. (1989).Statistique et modeles econometriques, Vol. I, II. Paris: Economica.Google Scholar
  10. Jöreskog, K. G. (1985, July).Estimation of the polyserial correlation from summary statistics. Paper presented at the Fourth European Meeting of the Psychometric Society in Cambridge, England.Google Scholar
  11. Jöreskog, K. G. (1991, July),Latent variable modeling with ordinal variables. Paper presented at the International Workshop on Statistical Modeling and Latent Variables in Trento, Italy.Google Scholar
  12. Jöreskog, K. G., & Sörbom, D. (1988).PRELIS—A program for multivariate data screening and data summarization. A preprocessor for LISREL (2nd ed.). Chicago, IL: Scientific Software.Google Scholar
  13. Jöreskog, K. G., & Sörbom, D. (1989).LISREL 7—A guide to the program and applications (2nd ed.). Chicago: SPSS Publications.Google Scholar
  14. Küsters, U. (1987). Hierarchische Mittlewert- und Kovarianzstrukturmodelle mit Nichtmetrischen Endogenen Variablen [Hierarchical mean—and covariance structure models with nonmetric endogenous variables]. Heidelberg: Physica-Verlag.Google Scholar
  15. Küsters, U. (1990). A note on sequential ML estimates and their asymptotic covariances.Statistical Papers, 31, 131–145.Google Scholar
  16. Lee, L.-F. (1982). Health and wage: A simultaneous equation model with multiple discrete indicators.International Economic Review, 23, 199–221.Google Scholar
  17. Lee, S.-Y., (1985). Maximum-likelihood estimation of polychoric correlations inr ×s ×t contingency tables.Journal of Statistical Computation and Simulations, 23, 53–67.Google Scholar
  18. Lee, S.-Y., & Poon, W.-Y. (1986). Maximum likelihood estimation of polyserial correlations.Psychometrika, 51, 113–121.Google Scholar
  19. Lee, S.-Y., & Poon, W.-Y. (1987). Two-step estimation of multivariate polychoric correlations.Communications in Statistics: Theory and Methods, 16, 307–320.Google Scholar
  20. Lee, S.-Y., Poon, W.-Y., & Bentler, P. M. (1989). Simultaneous analysis of multivariate polytomous variates in several groups.Psychometrika, 54, 63–73.Google Scholar
  21. Lee, S.-Y., Poon, W.-Y., & Bentler, P. M. (1990a). Full maximum likelihood analysis of structural equation models with polytomous variables.Statistics and Probability Letters, 9, 91–97.Google Scholar
  22. Lee, S.-Y., Poon, W.-Y., & Bentler, P. M. (1990b). A 3-stage estimation procedure for structural equation models with polytomous variables.Psychometrika, 55, 45–57.Google Scholar
  23. Lee, S.-Y., Poon, W.-Y., & Bentler, P. M. (1992). Structural equation models with continuous and polytomous variables.Psychometrika, 57, 89–105.Google Scholar
  24. Maddala, G. S. (1983).Limited-dependent and qualitative variables in econometrics. Cambridge: Cambridge University Press.Google Scholar
  25. Muthén, B. (1978). Contributions to factor analysis of dichotomous variables.Psychometrika, 43, 551–560.Google Scholar
  26. Muthén, B. (1979). A structural probit model with latent variables.Journal of the American Statistical Association, 74, 807–811.Google Scholar
  27. Muthén, B. (1983). Latent variable structural equation modeling with categorical data.Journal of Econometrics, 22, 48–65.Google Scholar
  28. Muthén, B. (1984). A general structural equation model with dichotomous, ordered categorical, and continuous latent variable indicators.Psychometrika, 49, 115–132.Google Scholar
  29. Muthén, B. (1987).LISCOMP. Analysis of linear structural equations with a comprehensive measurement model. Theoretical integration and user's guide. Mooresville, IN: Scientific Software.Google Scholar
  30. Muthén, B. (1989a). Multiple-group structural modeling with non-normal continuous variables.British Journal of Mathematical and Statistical Psychology, 42, 55–62.Google Scholar
  31. Muthén, B. (1989b). Tobit factor analysis.British Journal of Mathematical and Statistical Psychology, 42, 241–250.Google Scholar
  32. Muthén, B. (1989c). Latent variable modeling in heterogenous populations.Psychometrika, 54, 557–585. Presidential address to the Psychometric Society, July, 1989.Google Scholar
  33. Muthén, B. (1990). Moments of the censored and truncated bivariate normal distribution.British Journal of Mathematical and Statistical Psychology, 43, 131–143.Google Scholar
  34. Muthén, B. (1993). Goodness of fit with categorical and other non-normal variables. In K. Bollen & S. Long (Eds.), Testing structural equation models (pp. 205–243). Newbury Park: Sage Publications.Google Scholar
  35. Muthén, B., & Christofferson, A. (1981). Simultaneous factor analysis of dichotomous variables in several groups.Psychometrika, 46, 407–419.Google Scholar
  36. Muthén, B., & Kaplan, D. (1992). A comparison of some methologies for the factor analysis of non-normal Likert variables: A Note on the Size of the Model.British Journal of Mathematical and Statistical Psychology, 45, 19–30.Google Scholar
  37. Parke, W. (1986). Pseudo maximum likelihood estimation: The asymptotic distribution.The Annals of Statistics, 14, 355–357.Google Scholar
  38. Poon, W.-Y., & Lee, S.-Y. (1987). Maximum likelihood estimation of multivariate polyserial and polychoric correlation coefficients.Psychometrika, 52, 409–430.Google Scholar
  39. Poon, W.-Y., & Lee, S.-Y. (1988). Analyses of structural equation models with censored or truncated data (Technical report). Hong Kong: The Chinese University of Hong Kong, Department of Statistics.Google Scholar
  40. Poon, W.-Y., & Lee, S.-Y. (1992). Statistical analysis of continuous and polytomous variables in several populations.British Journal of Mathematical and Statistical Psychology, 45, 139–149.Google Scholar
  41. Satorra, A. (1992). Asymptotic robust inferences in the analysis of mean and covariance structures. In P. V. Marsden (Ed.),Sociological Methodology 1992 (pp. 249–278). New York: Plenum.Google Scholar
  42. Schepers, A. (1991). Numerische Verfahren und Implementation der Schatzung von Mittlewert und Kovarianz-Strukturmodellen mit Nichmetrische Variablen. Ahaus: Verlag Frank Hartman.Google Scholar
  43. Schepers, A., Arminger, G., & Küsters, U. (1992). The analysis of non-metric endogenous variables in latent variable models: The MECOSA approach. In P. Gruber (Ed.), Econometric decision models: New methods of modeling and applications. Lecture notes in mathematical systems (pp. 459–472). Heidelberg: Springer Verlag.Google Scholar
  44. Serfling, R. J. (1980).Approximation theorems of mathematical statistics. New York: Wiley.Google Scholar
  45. Sobel, M. E., & Arminger, G. (1992). Modeling household fertility decision: A non-linear simultaneous probit model.Journal of the American Statistical Association, 87, 38–47.Google Scholar

Copyright information

© The Psychometric Society 1995

Authors and Affiliations

  • Bengt O. Muthén
    • 1
  • Albert Satorra
    • 2
  1. 1.Graduate School of Education & Information StudiesUCLAUSA
  2. 2.Department of EconomicsUniversitat Pompeu FabraSpain

Personalised recommendations