An Introduction to Latent Variable Models

By B. Everitt. 1984

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

High-Dimensional Multivariate Forecasting with Low-Rank Gaussian Copula Processes (2019, methodology): “To alleviate these limitations, researchers have used dimensionality reduction methods and regularization, see for instance [3, 5] for VAR models and [34, 9] for MGARCH models, but these models remain unsuited for applications with more than a few hundreds dimensions [23].”
Adaptive computation and machine learning (1998, methodology): “In many models, it is typical to assume that the data result in part from the action of hidden or latent variables, or causes, that either are not available in the data gathered or perhaps are fundamentally unobservable [172].”
Model comparison of nonlinear structural equation models with fixed covariates (2003, background): “In past years, structural equation models (SEMs) have been applied extensively to important problems in behavioral, medical and social sciences (see, e.g., Bentler, 1983, 1992; Bollen & Long, 1993; Everitt, 1984; J/3reskog & S6rbom, 1996, among others).”
A Unifying Review of Linear Gaussian Models (1999, background): “See, for example, Everitt (1984).”
Experience and Expression: Social and Cultural Significance in the Fear of Crime (2004, unknown): “It has a number of other names, including LISREL (or linear structural relations—Hayduk, 1987; Jöreskog and Sörbom, 1988) causal modelling (Bentler, 1980; Reichardt and Gollob, 1986), latent variable models (Everitt, 1984), covariance structure analysis and analysis of covariance structures.”
A New Statistical Model for the Analysis of Customer Satisfaction (2010, unknown): “This approach has been accomplished in general (Everitt [12]; Bartholomew [5]), and also for ordinal data (Moustaki [27, 28]; Cagnone et al.”
Variational Learning in Nonlinear Gaussian Belief Networks (1999, methodology): “Two of the most tractable models of this kind are factor analysis (Everitt 1984) and independent component analysis (Comon, Jutten and Herault 1991; Bell and Sejnowski 1995; Amari, Cichocki and Yang 1996; MacKay 1997).”
A Framework for Robust Subspace Learning (2003, methodology): “A variety of linear learning models and techniques such as Principal Component Analysis (PCA) (Diamantaras, 1996; Neudecker and Magnus, 1999; Jolliffe, 1986; Mardia et al., 1979; Turk and Pentland, 1991), Factor Analysis (FA) ( Everitt, 1984; Mardia et al., 1979), Autoregressive analysis (AR) (Blak”
FABIA: factor analysis for bicluster acquisition (2010, methodology): “The formulation in Equation (2) facilitates a generative interpretation by a factor analysis model with p factors (Everitt, 1984) x = p∑ i=1 λi z̃i + = z̃ + , (3) where x is the observation, is the loading matrix, z̃i is the value of the i-th factor, z̃= (z̃1,...,z̃p)T is the vector of factors and…”
Using Generative Models for Handwritten Digit Recognition (1996, background): “What we have just described is an instantiation of the general framework of generative or latent variable models [32].”
Gaussian Process Latent Variable Models for Visualisation of High Dimensional Data (2003, methodology): “Factor analysis (Everitt, 1984) is a density estimation technique that assumes that the observed data were generated from a lower-dimensional process, characterized by k latent or hidden variables v that are all independently distributed with mean zero and unit variance.”
Fuzzy-Rough Sets Assisted Attribute Selection (2007, background): “In fact by using only the given information, the theory assumes that the data is a true and accurate reflection of the real world (which may not be the case).”
Hierarchical CUB Models for Ordinal Variables (2012, methodology): “Following the latent variable approach for the analysis of ordinal data (Everitt, 1984; Bartholomew, 1987; Sammel et al., 1997; Moustaki, 2000, 2003; Moustaki and Knott, 2000), we assume that the records are generated by an unobserved continuous random variable (say R∗); then, a correspondence with ”