Advances in Psychology Logo Advances in Psychology Logo
Methods | Special Issue: Network Psychometrics

A generalized approach for Bayesian Gaussian graphical models

Vithor Rosa Franco ORCID, Guilherme W. F. Barros ORCID, & Marcos Jiménez ORCID
https://doi.org/10.56296/aip00022
Published: August 16, 2024
Copyright: The authors (CC BY 4.0)

Franco, V.R., Barros, G.W.F., & Jiménez, M. (2024). A generalized approach for Bayesian Gaussian graphical models. advances.in/psychology, 2, e533499. https://doi.org/10.56296/aip00022

Franco, Vithor Rosa, et al. "A generalized approach for Bayesian Gaussian graphical models." advances.in/psychology, vol. 2, no. 1, 2024, e533499. https://doi.org/10.56296/aip00022.

Franco, Vithor Rosa, Guilherme W. F. Barros, and Marcos Jiménez. 2024. "A generalized approach for Bayesian Gaussian graphical models." advances.in/psychology 2 (1): e533499. https://doi.org/10.56296/aip00022.

Franco VR, Barros GWF, Jiménez M. A generalized approach for Bayesian Gaussian graphical models. advances.in/psychology. 2024;2(1):e533499. doi:10.56296/aip00022.

Franco, V.R. et al. (2024) 'A generalized approach for Bayesian Gaussian graphical models', advances.in/psychology, 2(1), e533499. Available at: https://doi.org/10.56296/aip00022.

Download .RIS Download .bib
Bayesian Gaussian Graphical Models (BGGMs) are tools of growing popularity and interest in network psychometrics and probabilistic graphical modeling. However, some of the existing models are derived from different modeling principles that do not easily allow for extensions and combinations into new models. More specifically, the implementation of some models may not be flexible enough to test different priors or likelihoods. In this paper, we present a new approach to BGGMs that overcomes this limitation by allowing for the estimation of regularized partial correlations between any type of variables while also having an intuitive approach on how to decide about the priors. Our approach is based on using a transformation of the lower diagonal values of the Cholesky (or LDL) decomposition matrix as the parameters of the models, which can receive any zero-centered symmetric distribution as a prior, as well as to include moderators. We have developed the gbggm R package to implement some models based on this approach, and the potentials of the approach are demonstrated with a toy simulation and an empirical example. This new approach expands the range of applications and enhances the flexibility of BGGMs, making them more useful in a variety of contexts.
  • Lin Yao, Wenxin Ge, Yue Zhao, Wanxin Wu, Zhuowen Wu, Lixin Hu, Xiuzhi Yang, Sichun Lin, Zhengge Jin, Jingyang Fang, Yajun Chen (2026). Comparative network analysis of emotional and behavioral health and mobile gaming addiction among adolescents with and without cyberbullying victimization experience: A large population-based study in China. Journal of Affective Disorders. https://doi.org/10.1016/j.jad.2025.121115
Download PDF Back to article