Abstract
This chapter shows that, starting from the two-way analysis of variance with random effects, it is possible to arrive at a general latent variable model. It does this, first by enlarging the family of conditional distributions considered and secondly, and more fundamentally, by allowing the random effect associated with the rows of the two-way table to be linear in a set of (unobserved) latent variables. In the case when the observed variables are conditionally normal, the standard model for factor analysis emerges but the framework adopted includes a great many other possibilities, including non-linear models. One advantage of adopting this general framework is that it makes the essential arbitrariness of the distribution of the latent variables transparent. It also paves the way for the following chapter in which we turn to clarifying what can be said about the prediction of the latent variables.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Reference
Bartholomew, D. J., Knott, M., & Moustaki, I. (2011). Latent variable models and factor analysis (3rd ed.). Chichester, UK: Wiley.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2013 The Author(s)
About this chapter
Cite this chapter
Bartholomew, D.J. (2013). A General Latent Variable Model. In: Unobserved Variables. SpringerBriefs in Statistics. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-39912-1_5
Download citation
DOI: https://doi.org/10.1007/978-3-642-39912-1_5
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-39911-4
Online ISBN: 978-3-642-39912-1
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)