Multiple testing and error control in Gaussian graphical model selection

DOI10.1214/088342307000000113zbMATH Open1246.62143arXivmath/0508267OpenAlexW1989373272WikidataQ57566446 ScholiaQ57566446MaRDI QIDQ449776FDOQ449776

Authors: Michael D. Perlman, Mathias Drton 

Publication date: 1 September 2012

Published in: Statistical Science (Search for Journal in Brave)

Abstract: Graphical models provide a framework for exploration of multivariate dependence patterns. The connection between graph and statistical model is made by identifying the vertices of the graph with the observed variables and translating the pattern of edges in the graph into a pattern of conditional independences that is imposed on the variables' joint distribution. Focusing on Gaussian models, we review classical graphical models. For these models the defining conditional independences are equivalent to vanishing of certain (partial) correlation coefficients associated with individual edges that are absent from the graph. Hence, Gaussian graphical model selection can be performed by multiple testing of hypotheses about vanishing (partial) correlation coefficients. We show and exemplify how this approach allows one to perform model selection while controlling error rates for incorrect edge inclusion.

Full work available at URL: https://arxiv.org/abs/math/0508267

Recommendations

• A SINful approach to Gaussian graphical model selection
• Model selection for Gaussian concentration graphs
• Gaussian graphical model estimation with false discovery rate control
• Multiple testing under dependence via graphical models
• Mixed Graphical Model Selection Using Holm's Procedure

zbMATH Keywords

Bayesian networksmultiple testingcovariance graphconcentration graphundirected graphacyclic directed graphchain graphDAGbidirected graphgraphical modesl

Mathematics Subject Classification ID

Applications of graph theory (05C90) Hypothesis testing in multivariate analysis (62H15) Measures of association (correlation, canonical correlation, etc.) (62H20) Directed graphs (digraphs), tournaments (05C20)

Cites Work

• Causation, prediction, and search
• Sparse graphical models for exploring gene expression data
• Experiments in stochastic computation for high-dimensional graphical models
• Introduction to Graphical Modelling
• Estimating the dimension of a model
• Asymptotic Statistics
• High-dimensional graphs and variable selection with the Lasso
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Graphical interaction models for multivariate time series.
• Graphical models for associations between variables, some of which are qualitative and some quantitative
• Hyper Markov laws in the statistical analysis of decomposable graphical models
• A characterization of Markov equivalence classes for acyclic digraphs
• Graphical models for genetic analyses
• The control of the false discovery rate in multiple testing under dependency.
• Learning Bayesian networks: The combination of knowledge and statistical data
• Generalizations of the familywise error rate
• Causal inference from graphical models
• Title not available (Why is that?)
• Gradient directed regularization for sparse Gaussian concentration graphs, with applications to inference of genetic networks
• A fast procedure for model search in multidimensional contingency tables
• Model Selection and Accounting for Model Uncertainty in Graphical Models Using Occam's Window
• Title not available (Why is that?)
• Title not available (Why is that?)
• 10.1162/153244302760200696
• Title not available (Why is that?)
• Rectangular Confidence Regions for the Means of Multivariate Normal Distributions
• Graphical models
• Ancestral graph Markov models.
• Title not available (Why is that?)
• Empirical Bayes Analysis of a Microarray Experiment
• Title not available (Why is that?)
• Linear dependencies represented by chain graphs. With comments and a rejoinder by the authors
• Model selection for Gaussian concentration graphs
• Lower bounds for the number of false null hypotheses for multiple testing of associations under general dependence structures
• Linear Recursive Equations, Covariance Selection, and Path Analysis
• Title not available (Why is that?)
• Covariance chains
• Probabilistic Networks and Expert Systems
• Multiple Testing. Part I. Single-Step Procedures for Control of General Type I Error Rates
• Title not available (Why is that?)
• Markov Properties for Acyclic Directed Mixed Graphs
• Multiple hypothesis testing in microarray experiments.
• A SINful approach to Gaussian graphical model selection
• Granger causality and path diagrams for multivariate time series
• Title not available (Why is that?)
• A robust procedure for Gaussian graphical model search from microarray data with \(p\) larger than \(n\)
• Estimation of a covariance matrix with zeros
• Hyper Inverse Wishart Distribution for Non-decomposable Graphs and its Application to Bayesian Inference for Gaussian Graphical Models
• Decomposable graphical Gaussian model determination
• On the Validity of the Markov Interpretation of Path Diagrams of Gaussian Structural Equations Systems with Correlated Errors
• A Monte Carlo method for computing the marginal likelihood in nondecomposable Gaussian graphical models
• Title not available (Why is that?)
• On chain graph models for description of conditional independence structures
• Title not available (Why is that?)
• Alternative Markov properties for chain graphs
• Title not available (Why is that?)
• Title not available (Why is that?)
• Graphical Models for Composable Finite Markov Processes
• Title not available (Why is that?)
• Analogies between Multiplicative Models in Contingency Tables and Covariance Selection
• Title not available (Why is that?)
• Separation and completeness properties for AMP chain graph Markov models.
• Normal linear regression models with recursive graphical Markov structure
• Choice of a null distribution in resampling-based multiple testing
• Characterizing Markov equivalence classes for AMP chain graph models
• Title not available (Why is that?)
• Maximum Likelihood Estimation in Gaussian Chain Graph Models under the Alternative Markov Property
• A mutagenetic tree hidden Markov model for longitudinal clonal HIV sequence data
• Title not available (Why is that?)
• A Fast Model Selection Procedure for Large Families of Models
• When should a learning machine ask for help?
• Title not available (Why is that?)
• The Isserlis matrix and its application to non-decomposable graphical Gaussian models
• A Graphical Chain Model Derived from a Model Selection Strategy for the Sociologists Graduates Study
• Decomposability and selection of graphical models for multivariate time series
• Compatible Prior Distributions for Directed Acyclic Graph Models
• Joint Response Graphs and Separation Induced by Triangular Systems
• On a Dualization of Graphical Gaussian Models: A Correction Note
• Low-Order Conditional Independence Graphs for Inferring Genetic Networks
• Some tests for correlation matrices

Cited In (44)

• High-dimensional semiparametric Gaussian copula graphical models
• Hypothesis Testing of Matrix Graph Model with Application to Brain Connectivity Analysis
• Inferring sparse Gaussian graphical models with latent structure
• Statistical inference for high-dimension, low-sample-size data
• Bayesian graph selection consistency under model misspecification
• Powerful multiple testing of paired null hypotheses using a latent graph model
• Robust identification in random variable networks
• Structure learning of exponential family graphical model with false discovery rate control
• Goodness-of-fit tests for high-dimensional Gaussian linear models
• Estimation of Gaussian graphs by model selection
• Maximum pairwise Bayes factors for covariance structure testing
• Support recovery of Gaussian graphical model with false discovery rate control
• Estimation of covariance and precision matrix, network structure, and a view toward systems biology
• GGM Knockoff Filter: False Discovery Rate Control for Gaussian Graphical Models
• Positive-definite thresholding estimators of covariance matrices with zeros
• Robust concentration graph model selection
• High-dimensional inference on covariance structures via the extended cross-data-matrix methodology
• Correlation tests for high-dimensional data using extended cross-data-matrix methodology
• Modeling dependent gene expression
• Gaussian graphical models with applications to omics analyses
• Objective Bayesian search of Gaussian directed acyclic graphical models for ordered variables with non-local priors
• Model selection for Gaussian concentration graphs
• On semiparametric exponential family graphical models
• A multitest procedure for testing MTP2 for Gaussian distributions
• A SINful approach to Gaussian graphical model selection
• Mixed Graphical Model Selection Using Holm's Procedure
• Gaussian graphical model estimation with false discovery rate control
• Structural similarity and difference testing on multiple sparse Gaussian graphical models
• Bayesian multiplicity control for multiple graphs
• Two-stage procedures for high-dimensional data
• On graphical models and convex geometry
• Regularized rank-based estimation of high-dimensional nonparanormal graphical models
• Uniformly most powerful unbiased test for conditional independence in Gaussian graphical model
• A review of Gaussian Markov models for conditional independence
• Robust graphical modeling of gene networks using classical and alternative \(t\)-distributions
• Exact test theory in Gaussian graphical models
• Tests for Gaussian graphical models
• Estimation of high-dimensional graphical models using regularized score matching
• Analysis of weakly correlated nodes in market network
• Some statistical problems with high dimensional financial data
• Effectiveness of combinations of Gaussian graphical models for model building
• Family-wise error rate control in Gaussian graphical model selection via distributionally robust optimization
• Large-scale correlation screening under dependence for brain functional connectivity network inference
• Loss function, unbiasedness, and optimality of Gaussian graphical model selection

Uses Software

• Resampling Stats
• TETRAD
• CoCo
• MIM
• HdBCS

This page was built for publication: Multiple testing and error control in Gaussian graphical model selection

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q449776)