A Three-Stage Estimation Procedure for Structural Equation Models with Polytomous Variables
- 1 March 1990
- journal article
- Published by Cambridge University Press (CUP) in Psychometrika
- Vol. 55 (1) , 45-51
- https://doi.org/10.1007/bf02294742
Abstract
This paper is concerned with the analysis of structural equation models with polytomous variables. A computationally efficient three-stage estimator of the thresholds and the covariance structure parameters, based on partition maximum likelihood and generalized least squares estimation, is proposed. An example is presented to illustrate the method.Keywords
This publication has 11 references indexed in Scilit:
- Full maximum likelihood analysis of structural equation models with polytomous variablesStatistics & Probability Letters, 1990
- Two-step estimation of multivariate polychoric correlationCommunications in Statistics - Theory and Methods, 1987
- Pseudo Maximum Likelihood Estimation: The Asymptotic DistributionThe Annals of Statistics, 1986
- Recent Developments in the Factor Analysis of Categorical VariablesJournal of Educational Statistics, 1986
- A general structural equation model with dichotomous, ordered categorical, and continuous latent variable indicatorsPsychometrika, 1984
- A Study of Algorithms for Covariance Structure Analysis with Specific Comparisons using Factor AnalysisPsychometrika, 1979
- Contributions to Factor Analysis of Dichotomous VariablesPsychometrika, 1978
- Factor Analysis of Dichotomized VariablesPsychometrika, 1975
- Fitting a Response Model for n Dichotomously Scored ItemsPsychometrika, 1970
- A Method of Generating Best Asymptotically Normal Estimates with Application to the Estimation of Bacterial DensitiesThe Annals of Mathematical Statistics, 1958