论文信息 - Full maximum likelihood analysis of structural equation models with polytomous variables

Full maximum likelihood analysis of structural equation models with polytomous variables

This paper is concerned with the analysis of structural equation models with polytomous variables. Identification conditions for the basic model are discussed. Theory for the full simultaneous maximum likelihood estimation of the thresholds and the covariance structure parameters is developed. An example is presented to illustrate the method.

[1] M. Schervish. Multivariate normal probabilities with error bound , 1984 .

[2] R. D. Bock,et al. Marginal maximum likelihood estimation of item parameters: Application of an EM algorithm , 1981 .

[3] B. Muthén. Contributions to factor analysis of dichotomous variables , 1978 .

[4] P. Bentler. Some contributions to efficient statistics in structural models: Specification and estimation of moment structures , 1983 .

[5] B. Muthén. A general structural equation model with dichotomous, ordered categorical, and continuous latent variable indicators , 1984 .

[6] R. Darrell Bock,et al. Fitting a response model forn dichotomously scored items , 1970 .

[7] Anders Christoffersson,et al. Factor analysis of dichotomized variables , 1975 .

[8] Wai-Yin Poon,et al. Maximum likelihood estimation of multivariate polyserial and polychoric correlation coefficients , 1988 .

[9] Sik-Yum Lee,et al. Further developments on constrained estimation in analysis of covariance structures , 1985 .