2010
DOI: 10.48550/arxiv.1011.6640
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

Extended Bayesian Information Criteria for Gaussian Graphical Models

Abstract: Gaussian graphical models with sparsity in the inverse covariance matrix are of significant interest in many modern applications. For the problem of recovering the graphical structure, information criteria provide useful optimization objectives for algorithms searching through sets of graphs or for selection of tuning parameters of other methods such as the graphical lasso, which is a likelihood penalization technique. In this paper we establish the consistency of an extended Bayesian information criterion for… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
29
0

Year Published

2013
2013
2024
2024

Publication Types

Select...
8
2

Relationship

0
10

Authors

Journals

citations
Cited by 42 publications
(29 citation statements)
references
References 8 publications
0
29
0
Order By: Relevance
“…To assess the trait-based network of boredom, curiosity, and exploration on an item level, we estimated a GGM with the EBICglasso algorithm (Chen & Chen, 2008; Epskamp & Fried, 2018; Foygel & Drton, 2010; Friedman et al, 2008). This part of the analysis was conducted in R (R Core Team, 2020) using the EGAnet (Golino & Christensen, 2019) and the qgraph packages (Epskamp et al, 2012, 2018).…”
Section: Methodsmentioning
confidence: 99%
“…To assess the trait-based network of boredom, curiosity, and exploration on an item level, we estimated a GGM with the EBICglasso algorithm (Chen & Chen, 2008; Epskamp & Fried, 2018; Foygel & Drton, 2010; Friedman et al, 2008). This part of the analysis was conducted in R (R Core Team, 2020) using the EGAnet (Golino & Christensen, 2019) and the qgraph packages (Epskamp et al, 2012, 2018).…”
Section: Methodsmentioning
confidence: 99%
“…For regularized network estimation (sparse Gaussian graphical model), graphical LASSO based on extended BIC criterion (EBICglasso) was used (Foygel and Drton, 2010;. The tuning parameter gamma was set to 0.5 and a threshold was applied to increase specificity.…”
Section: Cross-sectional Analysesmentioning
confidence: 99%
“…This value controls the trade-off between including false-positive edges and removing true edges. For the present study, the value of γ was set to 0.50, per recommendations by Foygel and Drton (2010). Node placement was determined by the Fruchterman-Reingold algorithm, which arranges nodes with stronger associations near the center of the graph and nodes with weaker average associations closer to the sides of the graph (Fruchterman & Reingold, 1991).…”
Section: Network Analysismentioning
confidence: 99%