BAYESIAN MODEL ASSESSMENT IN FACTOR ANALYSIS

By Hedibert Freitas Lopes, Matthew West. 2004

524 citations recorded by the source corpus.

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

Sparse Bayesian infinite factor models. (2011, background): “This constraint induces order dependence among the responses [Aguilar and West, 2000, West, 2003, Lopes and West, 2004], with the choice of the first k response variables being an important modeling decision [Carvalho et al., 2008].”
Model Averaging and Dimension Selection for the Singular Value Decomposition (2006, methodology): “For the factor analysis problem, Lopes and West (2004) devised a workable reversible-jump algorithm by constructing proposal distributions that approximate the within-model full conditional distributions of the model parameters.”
Model-Based Clustering (2016, background): “Lopes and West (2004) carry out simulation studies to demonstrate that the BIC can be effective for selection of the number of factors.”
A Bayesian Semiparametric Latent Variable Model for Mixed Responses (2007, unknown): “If (4) additionally contains a spatial effect f spat, a geoadditive LVM is obtained whose predictor is structured as in geoadditive models (see Kammann and Wand, 2003).”
Dynamic Hierarchical Factor Models (2013, methodology): “Kim and Nelson (2000) and Lopes and West (2004), among others, have used the algorithm proposed in Carter and Kohn (1994) and FrühwirthSchnatter (1994) to estimate two-level factor models with a single factor.”
Factor stochastic volatility with time varying loadings and Markov switching regimes (2007, methodology): “Lopes and West (2004) examine the problem of determining the number of factors in a static factor model while7 showing that the order of the variable is immaterial.”
Bayesian reasoning and machine learning (2012, unknown): “Bayesian extensions are clearly of interest; whilst formally intractable they can be addressed using approximate methods, for example [98, 178, 109].”
An adaptive scheduling scheme for calculating Bayes factors with thermodynamic integration using Simpson’s rule (2015, methodology): “For detailed overviews we refer to Friel and Wyse (2012), Lopes and West (2004), Kirk et al. (2013).”
Exploratory graph analysis: A new approach for estimating the number of dimensions in psychological research (2016, background): “Why does psychology need a new way to estimate the number of dimensions? The answer lies in the several studies published about the performance of the parallel analysis [18, 21, 22, 23, 24, 25], the MAP [18, 24, 26], the BIC [27, 28, 29, 30] and the Kaiser-Guttman eigenvalue rule [2, 18, 24, 25, 31]”
A Factor Analysis of Bond Risk Premia (2009, methodology): “For factor models, Kose, Otrok, and Whiteman (2003) uses an algorithm that involves 8 inversion of N matrices that are of dimension T ×T , which can be computationally demanding.”
bridgesampling: An R Package for Estimating Normalizing Constants (2017, unknown): “To identify the model, the factor loading matrix β is constrained to be lower-triangular (Lopes and West 2004).”
Spatial dynamic factor analysis (2008, methodology): “Lopes and West (2004) introduced a modern fully Bayesian treatment the number of common factor in standard normal linear factor analysis by means of a customized reversible jump MCMC (RJMCMC) scheme.”