Robust graphical modeling of gene networks using classical and alternative t-distributions

DOI10.1214/10-AOAS410zbMATH Open1232.62083arXiv1009.3669WikidataQ57566414 ScholiaQ57566414MaRDI QIDQ641155FDOQ641155

Authors: Michael Finegold, Mathias Drton 

Publication date: 21 October 2011

Published in: The Annals of Applied Statistics (Search for Journal in Brave)

Abstract: Graphical Gaussian models have proven to be useful tools for exploring network structures based on multivariate data. Applications to studies of gene expression have generated substantial interest in these models, and resulting recent progress includes the development of fitting methodology involving penalization of the likelihood function. In this paper we advocate the use of multivariate $t$-distributions for more robust inference of graphs. In particular, we demonstrate that penalized likelihood inference combined with an application of the EM algorithm provides a computationally efficient approach to model selection in the $t$-distribution case. We consider two versions of multivariate $t$-distributions, one of which requires the use of approximation techniques. For this distribution, we describe a Markov chain Monte Carlo EM algorithm based on a Gibbs sampler as well as a simple variational approximation that makes the resulting method feasible in large problems.

Full work available at URL: https://arxiv.org/abs/1009.3669

Recommendations

• Robust Bayesian graphical modeling using Dirichlet \(t\)-distributions
• Robust Gaussian graphical modeling via \(l_{1}\) penalization
• On robust Gaussian graphical modeling
• Robust sparse Gaussian graphical modeling
• Model selection and estimation in the matrix normal graphical model

zbMATH Keywords

Markov chain Monte CarloEM algorithmpenalized likelihoodgraphical modelmultivariate \(t\)-distributionrobust inference

Mathematics Subject Classification ID

Multivariate distribution of statistics (62H10) Applications of statistics to biology and medical sciences; meta analysis (62P10) Numerical analysis or methods applied to Markov chains (65C40) Applications of graph theory (05C90) Estimation in multivariate analysis (62H12)

Cites Work

• Graphical models, exponential families, and variational inference
• High-dimensional graphs and variable selection with the Lasso
• Multiple testing and error control in Gaussian graphical model selection
• Sparse inverse covariance estimation with the graphical lasso
• Model selection through sparse maximum likelihood estimation for multivariate Gaussian or binary data
• Model selection and estimation in the Gaussian graphical model
• Title not available (Why is that?)
• Title not available (Why is that?)
• Multivariate T-Distributions and Their Applications
• Linear Model Selection by Cross-Validation
• Title not available (Why is that?)
• Robust Gaussian graphical modeling
• Graphical methods for efficient likelihood inference in Gaussian covariance models

Cited In (49)

• Structured Shrinkage Priors
• Sparse precision matrices for minimum variance portfolios
• A horseshoe mixture model for Bayesian screening with an application to light sheet fluorescence microscopy in brain imaging
• A new multivariate t distribution with variant tail weights and its application in robust regression analysis
• Hierarchical normalized completely random measures for robust graphical modeling
• Order-invariant prior specification in Bayesian factor analysis
• A general family of trimmed estimators for robust high-dimensional data analysis
• Robust identification in random variable networks
• Robust sparse Gaussian graphical modeling
• On robust Gaussian graphical modeling
• Robust Gaussian graphical modeling via \(l_{1}\) penalization
• High-dimensional robust precision matrix estimation: cellwise corruption under \(\epsilon \)-contamination
• On the fractional moments of a truncated centered multivariate normal distribution
• Robust Bayesian graphical modeling using Dirichlet \(t\)-distributions
• Bayesian graphical models for modern biological applications
• Robust and sparse banking network estimation
• High-dimensional undirected graphical models for arbitrary mixed data
• Discussion to: Bayesian graphical models for modern biological applications by Y. Ni, V. Baladandayuthapani, M. Vannucci and F.C. Stingo
• Network tail risk estimation in the European banking system
• Robustly fitting Gaussian graphical models -- the R package robFitConGraph
• Title not available (Why is that?)
• Graphical models via univariate exponential family distributions
• Dimension-wise scaled normal mixtures with application to finance and biometry
• A 2-stage elastic net algorithm for estimation of sparse networks with heavy-tailed data
• Comment on article by Finegold and Drton
• Bayesian sparse seemingly unrelated regressions model with variable selection and covariance estimation via the horseshoe+
• Bayesian graphical modeling for heterogeneous causal effects
• Covariate-Assisted Bayesian Graph Learning for Heterogeneous Data
• MARS as an alternative approach of Gaussian graphical model for biochemical networks
• Covariance structure tests for multivariate \(t\)-distribution
• Robust and sparse estimation of the inverse covariance matrix using rank correlation measures
• Change points in heavy‐tailed multivariate time series: Methods using precision matrices
• Graphical models via joint quantile regression with component selection
• Stable graphical models
• Inferring network structure in non-normal and mixed discrete-continuous genomic data
• A new family of multivariate heavy-tailed distributions with variable marginal amounts of tailweight: application to robust clustering
• Graphical lassos for meta‐elliptical distributions
• A Bayesian graphical approach for large-scale portfolio management with fewer historical data
• Dynamic and robust Bayesian graphical models
• Robust estimation of sparse precision matrix using adaptive weighted graphical lasso approach
• Bayesian robust learning in chain graph models for integrative pharmacogenomics
• Rejoinder to the discussion of ``Bayesian graphical models for modern biological applications
• Estimation of high-dimensional graphical models using regularized score matching
• Quantile graphical models: a Bayesian approach
• Robust and sparse Gaussian graphical modelling under cell-wise contamination
• Nonparanormal graph quilting with applications to calcium imaging
• Groups acting on Gaussian graphical models
• Reversible MCMC on Markov equivalence classes of sparse directed acyclic graphs
• Robust methods for inferring sparse network structures

Uses Software

• glasso

This page was built for publication: Robust graphical modeling of gene networks using classical and alternative \(t\)-distributions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q641155)