Bayesian Gaussian Copula Factor Models for Mixed Data

Details Bayesian Gaussian Copula Factor Models for Mixed Data Bayesian Gaussian Copula Factor Models for Mixed Data

2011-11-01

arxiv.org/abs/1111.0317v1

Statistics

Methodology

R package accompanying this paper is available here: http://stat.duke.edu/~jsm38/software/bfa

Scientific paper

Gaussian factor models have proven widely useful for parsimoniously characterizing dependence in multivariate data. There is a rich literature on their extension to mixed categorical and continuous variables, using latent Gaussian variables or through generalized latent trait models acommodating measurements in the exponential family. However, when generalizing to non-Gaussian measured variables the latent variables typically influence both the dependence structure and the form of the marginal distributions, complicating interpretation and introducing artifacts. To address this problem we propose a novel class of Bayesian Gaussian copula factor models which decouple the latent factors from the marginal distributions. A semiparametric specification for the marginals based on the extended rank likelihood yields straightforward implementation and substantial computational gains, critical for scaling to high-dimensional applications. We provide new theoretical and empirical justifications for using this likelihood in Bayesian inference. We propose new default priors for the factor loadings and develop efficient parameter-expanded Gibbs sampling for posterior computation. The methods are evaluated through simulations and applied to a dataset in political science. We also provide bfa, an easy-to-use R package leveraging compiled code to fit the models in this paper.

Affiliated with

Also associated with

No associations

Rating

Bayesian Gaussian Copula Factor Models for Mixed Data does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Bayesian Gaussian Copula Factor Models for Mixed Data, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Bayesian Gaussian Copula Factor Models for Mixed Data will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-327040