State of the aRt personality research: A tutorial on network analysis of personality data in R
Introduction
A network is an abstract model composed of a set of nodes or vertices, a set of edges, links or ties that connect the nodes, together with information concerning the nature of the nodes and edges (e.g., De Nooy, Mrvar, & Batagelj, 2011). Fig. 1 reports the example of a simple network, with six nodes and seven edges. The nodes usually represent entities and the edges represent their relations. This simple model can be used to describe many kinds of phenomena, such as social relations, technological and biological structures, and information networks (e.g., Newman, 2010, Chapters 2–5). Recently networks of relations among thoughts, feelings and behaviors have been proposed as models of personality and of psychopathology: in this framework, traits have been conceived of as emerging phenomena that arise from such networks (Borsboom and Cramer, 2013, Cramer et al., 2012a, Schmittmann et al., 2013). An R package, qgraph, has been developed for the specific purpose of analyzing personality and psychopathology data (Epskamp, Cramer, Waldorp, Schmittmann, & Borsboom, 2012).
The aim of this contribution is to provide the reader with the necessary theoretical and methodological tools to analyze personality data using network analysis, by presenting key network concepts, instructions for applying them in R (R Core Team, 2013), and examples based on simulated and on real data. First, we show how a network can be defined from personality data. Second, we present a brief overview of important network concepts. Then, we discuss how network concepts can be applied to personality data using R. In the last part of the paper, we outline how network-based simulations can be performed that are specifically relevant for personality psychology. Both the data and the R code are available for the reader to replicate our analyses and to perform similar analyses on his/her own data.
Section snippets
Constructing personality networks
A typical personality data set consists of cross-sectional measures of multiple subjects on a set of items designed to measure several facets of personality. In standard approaches in personality research, such data are used in factor analysis to search for an underlying set of latent variables that can explain the structural covariation in the data. In a causal interpretation of latent variables (Borsboom, Mellenbergh, & van Heerden, 2003), responses to items such as “I like to go to parties”
Analyzing the structure of personality networks
Once a network is estimated, several indices can be computed that convey information about network structure.
Simulating personality networks
In addition to the analysis of empirical data, network modeling offers extensive possibilities in the area of theory development. This is because, in contrast to purely data analytic models like factor analysis, networks are naturally coupled to dynamics (e.g., see Kolaczyk, 2009): they can evolve, grow, and change over time, with direct consequences for their dynamic behavior. This makes it possible to start thinking about questions like: How do personality networks form in development? Do
Discussion
Network approaches offer a rich trove of novel insights into the organization, emergence, and dynamics of personality. By integrating theoretical considerations (Cramer et al., 2010), simulation models (Mõttus et al., unpublished results, van der Maas et al., 2006), and flexible yet user-friendly data-analytic techniques (Epskamp et al., 2012), network approaches have potential to achieve a tighter fit between theory and data analysis than has previously been achieved in personality research.
Acknowledgments
This work was supported by Fondazione Cariplo research Grant “Dottorato ad alta formazione in Psicologia Sperimentale e Neuroscienze Cognitive” (Advanced education doctorate in experimental psychology and cognitive neurosciences), Grant Number 2010-1432 (awarded to Giulio Costantini) and by NWO “research talent” Grant Number 406-11-066 (awarded to Sacha Epskamp).
References (106)
- et al.
Complex networks: Structure and dynamics
Physics Reports
(2006) Some unique properties of eigenvector centrality
Social Networks
(2007)- et al.
Eigenvector-like measures of centrality for asymmetric relations
Social Networks
(2001) Centrality and network flow
Social Networks
(2005)- et al.
A Graph-theoretic perspective on centrality
Social Networks
(2006) On variants of shortest-path betweenness centrality and their generic computation
Social Networks
(2008)- et al.
Error and attack tolerance of complex networks
Physica A
(2004) Centrality in social networks conceptual clarification
Social Networks
(1978)- et al.
Centrality in valued graphs: A measure of betweenness based on network flow
Social Networks
(1991) A general factor of personality: Evidence for the Big One in the five-factor model
Journal of Research in Personality
(2007)
A measure of betweenness centrality based on random walks
Social Networks
Node centrality in weighted networks: Generalizing degree and shortest paths
Social Networks
Clustering in weighted networks
Social Networks
Item selection, evaluation, and simple structure in personality data
Journal of Research in Personality
Constructs of social and emotional effectiveness: Different labels, same content?
Journal of Research in Personality
Deconstructing the construct: A network perspective on psychological phenomena
New Ideas in Psychology
Situation trait relevance, trait expression, and cross-situational consistency: Testing a principle of trait activation
Journal of Research in Personality
A defence of the lexical approach to the study of personality structure
European Journal of Personality
Empirical, theoretical, and practical advantages of the HEXACO model of personality structure
Personality and Social Psychology Review
The HEXACO-60: A short measure of the major dimensions of personality
Journal of Personality Assessment
Scale-free networks
Scientific American
The architecture of complex weighted networks
Proceedings of the National Academy of Sciences of the United States of America
Factoring and weighting approaches to status scores and clique identification
The Journal of Mathematical Sociology
Power and centrality: A family of measures
American Journal of Sociology
Measuring the mind: Conceptual issues in contemporary psychometrics
Network analysis: An integrative approach to the structure of psychopathology
Annual Review of Clinical Psychology
The small world of psychopathology
PLoS ONE
The theoretical status of latent variables
Psychological Review
A faster algorithm for betweenness centrality
The Journal of Mathematical Sociology
Centrality measures based on current flow
A network approach to psychopathology: New insights into clinical longitudinal data
PLoS ONE
Social network analysis: A methodological introduction
Asian Journal of Social Psychology
Social network analysis with sna
Journal of Statistical Software
Convergent and discriminant validation by the multitrait–multimethod matrix
Psychological Bulletin
Personality architecture: Within-person structures and processes
Annual Review of Psychology
Latent variable graphical model selection via convex optimization
The Annals of Statistics
Professional manual: Revised NEO Personality Inventory (NEO PI-R) and NEO Five-Factor Inventory (NEO-FFI)
Generalization of clustering coefficients to signed correlation networks
PLoS ONE
Linear dependencies represented by chain graphs
Statistical Science
Dimensions of normal personality as networks in search of equilibrium: You can’t like parties if you don’t like people
European Journal of Personality
Measurable like temperature or mereological like flocking? On the nature of personality traits
European Journal of Personality
Comorbidity: A network perspective
Behavioral and Brain Sciences
The igraph software package for complex network research
InterJournal Complex Systems
Exploratory social network analysis with Pajek
Towards a pan-cultural personality structure: Input from 11 psycholexical studies
European Journal of Personality
A note on two problems in connexion with graphs
Numerische Mathematik
Testing measurement invariance in the target rotated multigroup exploratory factor model
Structural Equation Modeling
Model selection for Gaussian concentration graphs
Biometrika
Qgraph: Network visualizations of relationships in psychometric data
Journal of Statistical Software
Network exploration via the adaptive LASSO and SCAD penalties
The Annals of Applied Statistics
Cited by (553)
Validation of the Emotional Skills and Competence Questionnaire in Croatian and Portuguese samples using exploratory graph analysis
2024, Personality and Individual DifferencesSleep and daytime functioning in autistic teenagers: A psychological network approach
2024, Research in Autism Spectrum Disorders
- 1
The first two authors contributed equally to this work.