A Tutorial on Regularized Partial Correlation Networks

By Sacha Epskamp, Eiko I. Fried. Psychological methods, 2016

2,425 citations recorded by the source corpus.

Abstract Recent years have seen an emergence of network modeling applied to moods, attitudes, and problems in the realm of psychology. In this framework, psychological variables are understood to directly affect each other rather than being caused by an unobserved latent entity. In this tutorial, we introduce the reader to estimating the most popular network model for psychological data: the partial correlation network. We describe how regularization techniques can be used to efficiently estimate a parsimonious and interpretable network structure in psychological data. We show how to perform these analyses in R and demonstrate the method in an empirical example on posttraumatic stress disorder data. In addition, we discuss the effect of the hyperparameter that needs to be manually set by the researcher, how to handle non-normal data, how to determine the required sample size for a network analysis, and provide a checklist with potential solutions for problems that can arise when estimating regularized partial correlation networks.

Subfields: Cognitive Neuroscience, Experimental and Cognitive Psychology, Statistical and Nonlinear Physics

View Paper: https://www.semanticscholar.org/paper/dae85e27ee2fc60e466da7ff77dae918c4f03a4b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Experimental and Cognitive Psychology

In Statistical and Nonlinear Physics

Citations in the corpus

Comparing network structures on three aspects: A permutation test. (2022, methodology): “…estimate these models, such as the methods that will be used in this study: EBICglasso for normally distributed variables COMPARING NETWORK STRUCTURES ON THREE ASPECTS 9 (Epskamp & Fried, 2018) IsingFit for binary variables (Van Borkulo et al., 2014), implemented in R package qgraph and IsingFit.”
Emotion Regulation Difficulties Related to Depression and Anxiety: A Network Approach to Model Relations Among Symptoms, Positive Reappraisal, and Repetitive Negative Thinking (2019, methodology): “The GGM tuning parameter was set to the conservative value of 0.5 to increase the specificity of the estimated networks (Epskamp & Fried, 2016).”
Investigating the performance of Exploratory Graph analysis and traditional techniques to identify the number of latent factors: a simulation and tutorial (2018, methodology): “Absent edges represent zero partial correlations (conditionally independent variables) while nonabsent edges represent the remaining association between two variables after controlling for all other variables (Epskamp & Fried, 2018; Epskamp et al., 2017).”
A Psychometric Network Perspective on the Validity and Validation of Personality Trait Questionnaires (2019, background): “Psychometric network models have a simple representation: nodes (circles) represent variables (e.g. questionnaire items), and edges (lines) represent the unique associations (e.g. partial correlations) between nodes (Epskamp and Fried, 2018; Epskamp et al., 2018b).”
Unpacking Rumination and Executive Control: A Network Perspective (2017, methodology): “In this network, edges represent conditional independence relationships between nodes when controlling for the effects of all other nodes (Epskamp & Fried, 2016).”
Who Is Impacted? Personality Predicts Individual Differences in Psychological Consequences of the COVID-19 Pandemic in Germany (2020, background): “…regressions should not or cannot be interpreted (e.g., Dark Triad literature: Sleep et al., 2017; Vize et al., 2018), while other literature routinely makes uses of partial effects (e.g., network literature: Epskamp & Fried, 2018) or provides cautious interpretations (e.g., Furnham et al., 2013).”
Moving Forward: Challenges and Directions for Psychopathological Network Theory and Methodology (2017, methodology): “Regularization techniques try to explain the covariance among symptoms with as few connections as possible and reduce the danger of overfitting by shrinking all connections and by setting small coefficients exactly to zero (Epskamp & Fried, 2016).”
Estimating psychological networks and their accuracy: A tutorial paper (2016, positive): “We estimated Gaussian graphical models, using the graphical LASSO in combination with EBIC model selection (Epskamp and Fried, 2016; Foygel and Drton, 2010), using polychoric correlation matrices as input.”
Income insufficiency impacts early brain development in infants facing increased psychosocial adversity: A network-based approach (2026, unknown): “EGA removes weak and multicollinear associations using penalized maximum likelihood estimation (22 ), resulting in the disconnection of such nodes in the network representation.”