Lattices of graphical Gaussian models with symmetries

DOI10.3390/SYM3030653zbMATH Open1360.62266arXiv1104.1608OpenAlexW3103411272MaRDI QIDQ527583FDOQ527583

Authors: Helene Gehrmann 

Publication date: 12 May 2017

Published in: Symmetry (Search for Journal in Brave)

Abstract: In order to make graphical Gaussian models a viable modelling tool when the number of variables outgrows the number of observations, model classes which place equality restrictions on concentrations or partial correlations have previously been introduced in the literature. The models can be represented by vertex and edge coloured graphs. The need for model selection methods makes it imperative to understand the structure of model classes. We identify four model classes that form complete lattices of models with respect to model inclusion, which qualifies them for an Edwards-Havr'anek model selection procedure. Two classes turn out most suitable for a corresponding model search. We obtain an explicit search algorithm for one of them and provide a model search example for the other.

Full work available at URL: https://arxiv.org/abs/1104.1608

Recommendations

• Graphical Gaussian Models With Edge and Vertex Symmetries
• Model selection for Gaussian concentration graphs
• Coloured graphical models and their symmetries
• A SINful approach to Gaussian graphical model selection
• Graphical models for sparse data: graphical Gaussian models with vertex and edge symmetries

zbMATH Keywords

model selectioncovariance selectioninvariancepermutation symmetryconditional independencepatterned covariance matrices

Mathematics Subject Classification ID

Parametric inference (62F99) Estimation in multivariate analysis (62H12)

Cited In (9)

• Coloured graphical models and their symmetries
• Symmetrically Colored Gaussian Graphical Models with Toric Vanishing Ideals
• Linear estimating equations for exponential families with application to Gaussian linear concentration models
• Estimation of means in graphical Gaussian models with symmetries
• Model selection for Gaussian concentration graphs
• Bayesian model selection approach for coloured graphical Gaussian models
• Model selection in the space of Gaussian models invariant by symmetry
• On the application of Gaussian graphical models to paired data problems
• The correlation space of Gaussian latent tree models and model selection without fitting

Uses Software

• gRc
• glasso
• MIM

This page was built for publication: Lattices of graphical Gaussian models with symmetries

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q527583)