Parameterizing Inequality Constraints on Unique Variances in Linear Structural Models
- 1 March 1983
- journal article
- Published by Cambridge University Press (CUP) in Psychometrika
- Vol. 48 (1) , 73-83
- https://doi.org/10.1007/bf02314677
Abstract
Current computer programs for analyzing linear structural models will apparently handle only two types of constraints: fixed parameters, and equality of parameters. An important constraint not handled is inequality; this is particularly crucial for preventing negative variance estimates. In this paper, a method is described for imposing several kinds of inequality constraints in models, without the necessity for having computer programs which explicitly allow such constraints. The examples discussed include the prevention of Heywood cases, extension to inequalities of parameters to be greater than a specified value, and imposing ordered inequalities.Keywords
This publication has 5 references indexed in Scilit:
- A simple comprehensive model for the analysis of covariance structures: Some remarks on applicationsBritish Journal of Mathematical and Statistical Psychology, 1980
- Linear Structural Equations with Latent VariablesPsychometrika, 1980
- Estimation of Covariance Structure Models with Parameters Subject to Functional RestraintsPsychometrika, 1980
- Multistructure Statistical Model Applied To Factor AnalysisMultivariate Behavioral Research, 1976
- ESTIMATION AND TESTING OF SIMPLEX MODELSBritish Journal of Mathematical and Statistical Psychology, 1970