Bayesian modeling of temporal dependence in large sparse contingency tables

DOI10.1080/01621459.2013.823866zbMATH Open1283.62120arXiv1205.2816OpenAlexW2094903679WikidataQ37523771 ScholiaQ37523771MaRDI QIDQ5406360FDOQ5406360

Authors: T. Kunihama, David Dunson 

Publication date: 1 April 2014

Published in: Journal of the American Statistical Association (Search for Journal in Brave)

Abstract: In many applications, it is of interest to study trends over time in relationships among categorical variables, such as age group, ethnicity, religious affiliation, political party and preference for particular policies. At each time point, a sample of individuals provide responses to a set of questions, with different individuals sampled at each time. In such settings, there tends to be abundant missing data and the variables being measured may change over time. At each time point, one obtains a large sparse contingency table, with the number of cells often much larger than the number of individuals being surveyed. To borrow information across time in modeling large sparse contingency tables, we propose a Bayesian autoregressive tensor factorization approach. The proposed model relies on a probabilistic Parafac factorization of the joint pmf characterizing the categorical data distribution at each time point, with autocorrelation included across times. Efficient computational methods are developed relying on MCMC. The methods are evaluated through simulation examples and applied to social survey data.

Full work available at URL: https://arxiv.org/abs/1205.2816

Recommendations

• Bayesian factorizations of big sparse tensors
• Modeling associations among multivariate longitudinal categorical variables in survey data: a semiparametric Bayesian approach
• Categorical time series models for contingency tables
• Dynamic association modeling in \(2\times 2\) contingency tables
• Alternative statistical models and representations for large sparse multi-dimensional contingency tables

zbMATH Keywords

panel datadynamic modelsnonparametric BayesParafacmultivariate categorical datastick-breakingprobabilistic tensor factorization

Mathematics Subject Classification ID

Bayesian inference (62F15) Numerical analysis or methods applied to Markov chains (65C40) Contingency tables (62H17) Applications of statistics to social sciences (62P25) Nonparametric inference (62G99)

Cites Work

• Nonparametric Bayesian models through probit stick-breaking processes
• Nonparametric Bayes conditional distribution modeling with variable selection
• Title not available (Why is that?)
• Sampling the Dirichlet Mixture Model with Slices
• DATA AUGMENTATION AND DYNAMIC LINEAR MODELS
• On Gibbs sampling for state space models
• A simple and efficient simulation smoother for state space time series analysis
• Order-Based Dependent Dirichlet Processes
• Three centuries of categorical data analysis: Log-linear models and maximum likelihood estima\-tion
• Orthogonal tensor decompositions
• Bayesian dynamic modeling of latent trait distributions
• The simulation smoother for time series models
• Simplex factor models for multivariate unordered categorical data
• Nonparametric Bayes modeling of multivariate categorical data
• Dynamic Nonparametric Bayesian Models for Analysis of Music
• Copula Gaussian graphical models and their application to modeling functional disability data
• A semiparametric Bayesian model for randomised block designs
• Slice sampling mixture models
• Retrospective Markov chain Monte Carlo methods for Dirichlet process hierarchical models
• Gibbs Sampling Methods for Stick-Breaking Priors
• Bayesian dynamic density estimation
• The local Dirichlet process
• Sequential Ordinal Modeling with Applications to Survival Data

Cited In (8)

• Bayesian inference on group differences in multivariate categorical data
• Modeling dependence structures for response times in a Bayesian framework
• Smoothing sparse contingency tables: a graphical Bayesian approach
• Dynamic modeling of the Italians' attitude towards Covid-19
• Modeling association in microbial communities with clique loglinear models
• Loglinear model selection and human mobility
• Nonparametric Bayes modeling for case control studies with many predictors
• Incorporating marginal prior information in latent class models

This page was built for publication: Bayesian modeling of temporal dependence in large sparse contingency tables

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5406360)