The Gaussian Graphical Model in Cross-Sectional and Time-Series Data

2016/09/30 by Sacha Epskamp, Lourens Waldorp, Lourens J. Waldorp +2 · 1,186 citations
Agricultural and Biological Sciences · Computer Science · Mathematics · Psychology · #Artificial intelligence #Cognitive Science and Mapping #Computer science #Data mining #Econometrics #Gaussian #Graphical model #Machine learning #Mathematics #Mental Health Research Topics #Sensory Analysis and Statistical Methods #Series (stratigraphy) #Statistics #Time series #stat.AP #stat.ME

paper · pdf · doi:10.1080/00273171.2018.1454823

published in Multivariate Behavioral Research 53(4), 453-480 (Taylor & Francis) · Accepted pending revision in Multivariate Behavioral Research

openalex publication_date 2018/04/16 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/06

Abstract

We discuss the Gaussian graphical model (GGM; an undirected network of partial correlation coefficients) and detail its utility as an exploratory data analysis tool. The GGM shows which variables predict one-another, allows for sparse modeling of covariance structures, and may highlight potential causal relationships between observed variables. We describe the utility in three kinds of psychological data sets: data sets in which consecutive cases are assumed independent (e.g., cross-sectional data), temporally ordered data sets (e.g., n = 1 time series), and a mixture of the 2 (e.g., n > 1 time series). In time-series analysis, the GGM can be used to model the residual structure of a vector-autoregression analysis (VAR), also termed graphical VAR. Two network models can then be obtained: a temporal network and a contemporaneous network. When analyzing data from multiple subjects, a GGM can also be formed on the covariance structure of stationary means-the between-subjects network. We discuss the interpretation of these models and propose estimation methods to obtain these networks, which we implement in the R packages graphicalVAR and mlVAR. The methods are showcased in two empirical examples, and simulation studies on these methods are included in the supplementary materials.

Citations

• An Introduction to the Five‐Factor Model and Its Applications
• Experience sampling research in psychopathology: opening the black box of daily life
• Investigating Causal Relations by Econometric Models and Cross-spectral Methods

Cited by

• Bayesian Estimation for Gaussian Graphical Models: Structure Learning, Predictability, and Network Comparisons
• Methodological and Statistical Practices of Using Symptom Networks to Evaluate Mental Health Interventions: A Review and Reflections
• Psychometric Network Models from Time-Series and Panel Data
• Cognitive Variables in Social Anxiety Disorder in Children and Adolescents: A Network Analysis
• Meeting the Bare Minimum: Quality Assessment of Idiographic Temporal Networks Using Power Analysis and Predictive-Accuracy Analysis
• Multi‐response phylogenetic mixed models: concepts and application
• Descriptive, Predictive and Explanatory Personality Research: Different Goals, Different Approaches, but a Shared Need to Move beyond the Big Few Traits
• How do people understand inequality in Chile? A study through attitude network analysis
• Executive Functioning, Internalizing and Externalizing Symptoms: Understanding Developmental Dynamics Through Panel Network Approaches
• Towards precision in the diagnostic profiling of patients: leveraging symptom dynamics as a clinical characterisation dimension in the assessment of major depressive disorder
• Structured Estimation of Heterogeneous Time Series
• Must We Always Go Idiographic?
• Digital personomics: precision and digital psychiatry beyond reductionism
• Societal spirits in the silver streak: Unraveling complexity in drinking habits of the mature adult population
• A longitudinal network analysis of suicide risk factors among service members and veterans sampled for suicidal ideation or attempt
• “Rejection Makes Me Suspicious”: Complex Temporal Network Approach to the Dynamics of Real-Time Paranoid Thoughts and Psychological Vulnerability
• Same same but different: Threat expectancy change and fear reduction as readouts of exposure rationales are only weakly associated and contribute differentially to treatment outcome in anxiety disorders
• When eco-anger (but not eco-anxiety nor eco-sadness) makes you change! A temporal network approach to the emotional experience of climate change
• Comparing network structures on three aspects: A permutation test.
• The dynamic interplay between mental health difficulties and the family environment in early adolescence
• Emotionally Vulnerable Subtype of Internet Gaming Disorder: Measuring and Exploring the Pathology of Problematic Generative AI Use
• Within-Person Temporal Associations Among Self-Reported Physical Activity, Sleep, and Well-Being in College Students
• Social media use and well-being: A prospective experience-sampling study
• High-resolution characterization of nasal microbial dynamics in young children
• Psychological flexibility and cognitive-affective processes in young adults’ daily lives
• Human-AI collaboration or obedient and often clueless AI in instruct, serve, repeat dynamics?
• Intrinsic and extrinsic social comparisons in online and offline contexts: An ecological momentary assessment study of associations with wellbeing
• Reporting standards for psychological network analyses in cross-sectional data.
• Graph recovery from graph wave equation
• Temporal Dynamics Between State Attachment Security, Avoidance, and Anxiety: Insights into Everyday Attachment System Functioning
• Causal discovery analysis: A promising tool in advancing precision medicine for eating disorders
• Predictors of substance use during treatment for addiction: A network analysis of ecological momentary assessment data
• Beyond linear mediation: Toward a dynamic network approach to study treatment processes
• Minimax entropy: The statistical physics of optimal models
• High-dimensional structure learning of sparse vector autoregressive models using fractional marginal pseudo-likelihood
• Toward incorporating genetic risk scores into symptom networks of psychosis. [europepmc]
• Back to the basics: Rethinking partial correlation network methodology. [europepmc]
• A Clinician’s Primer for Idiographic Research: Considerations and Recommendations. [europepmc]
• The Differential Role of Central and Bridge Symptoms in Deactivating Psychopathological Networks. [europepmc]
• The network approach to posttraumatic stress disorder: a systematic review. [europepmc]
• Beyond linear mediation: Toward a dynamic network approach to study treatment processes. [europepmc]
• Toward an Integrative Psychometric Model of Emotions. [europepmc]
• Comparing Gaussian graphical models with the posterior predictive distribution and Bayesian model selection. [europepmc]
• Psychometric network models from time-series and panel data. [europepmc]
• Investigating the performance of exploratory graph analysis and traditional techniques to identify the number of latent factors: A simulation and tutorial. [europepmc]
• Associations between moral injury, PTSD clusters, and depression among Israeli veterans: a network approach. [europepmc]
• On the validity of the centrality hypothesis in cross-sectional between-subject networks of psychopathology. [europepmc]
• General psychopathology links burden of recent life events and psychotic symptoms in a network approach. [europepmc]
• Health Care Workers' Mental Health During the First Weeks of the SARS-CoV-2 Pandemic in Switzerland-A Cross-Sectional Study. [europepmc]
• Network structure of depression and anxiety symptoms in Chinese female nursing students. [europepmc]
• Studying Behaviour Change Mechanisms under Complexity. [europepmc]
• Estimating group differences in network models using moderation analysis. [europepmc]
• On the Control of Psychological Networks. [europepmc]
• The item network and domain network of burnout in Chinese nurses. [europepmc]
• Modeling psychopathology: From data models to formal theories. [europepmc]
• Within- and across-day patterns of interplay between depressive symptoms and related psychopathological processes: a dynamic network approach during the COVID-19 pandemic. [europepmc]
• Network analysis of depressive and anxiety symptoms in adolescents during and after the COVID-19 outbreak peak. [europepmc]
• Risk and Protective Factors in Adolescent Suicidal Behaviour: A Network Analysis. [europepmc]
• A network approach can improve eating disorder conceptualization and treatment. [europepmc]
• Network analysis: An overview for mental health research. [europepmc]

Related

• The Gaussian Graphical Model in Cross-sectional and Time-series Data
• Psychometric Network Models from Time-Series and Panel Data
• Relations between networks, regression, partial correlation, and latent variable model
• Brief Report on Estimating Regularized Gaussian Networks from Continuous and Ordinal Data
• Bayesian Estimation for Gaussian Graphical Models: Structure Learning, Predictability, and Network Comparisons