Abstract
Abstract An introduction to latent variable covariance structure models is provided. Estimation and testing of such models with normal and non-normal variables is reviewed, and a relatively inexpensive asymptotically distribution-free estimator is introduced. The traditional econometric simultaneous equation system is reconceptualized as a random vector structural equation model. Extensions of the model to deal with latent variables and a wider variety of structural phenomena are made via the Joreskog-Keesling-Wiley LISREL approach and a simpler approach due to Bentler and Weeks. These representation systems are extended via first and second moments about the origin of measured variables, explained in terms of the structural coefficients and the moments of explanatory variables. Citations to further literature are provided.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
