Generalized Network Psychometrics: Combining Network and Latent Variable Models

We introduce the network model as a formal psychometric model, conceptualizing the covariance between psychometric indicators as resulting from pairwise interactions between observable variables in a network structure. This contrasts with standard psychometric models, in which the covariance between test items arises from the influence of one or more common latent variables. Here, we present two generalizations of the network model that encompass latent variable structures, establishing network modeling as parts of the more general framework of structural equation modeling (SEM). In the first generalization, we model the covariance structure of latent variables as a network. We term this framework latent network modeling (LNM) and show that, with LNM, a unique structure of conditional independence relationships between latent variables can be obtained in an explorative manner. In the second generalization, the residual variance–covariance structure of indicators is modeled as a network. We term this generalization residual network modeling (RNM) and show that, within this framework, identifiable models can be obtained in which local independence is structurally violated. These generalizations allow for a general modeling framework that can be used to fit, and compare, SEM models, network models, and the RNM and LNM generalizations. This methodology has been implemented in the free-to-use software package lvnet, which contains confirmatory model testing as well as two exploratory search algorithms: stepwise search algorithms for low-dimensional datasets and penalized maximum likelihood estimation for larger datasets. We show in simulation studies that these search algorithms perform adequately in identifying the structure of the relevant residual or latent networks. We further demonstrate the utility of these generalizations in an empirical example on a personality inventory dataset.

[1]  Gunter Maris,et al.  Bayesian inference for low-rank Ising networks , 2015, Scientific Reports.

[2]  H. Zou,et al.  Regularization and variable selection via the elastic net , 2005 .

[3]  Claudia D. van Borkulo,et al.  A Network Approach to Psychosis: Pathways Between Childhood Trauma and Psychotic Symptoms , 2017, Schizophrenia bulletin.

[4]  Francis Tuerlinckx,et al.  From loss to loneliness: The relationship between bereavement and depressive symptoms. , 2015, Journal of abnormal psychology.

[5]  D. Borsboom,et al.  Deconstructing the construct: A network perspective on psychological phenomena , 2013 .

[6]  D. Lawley VI.—The Estimation of Factor Loadings by the Method of Maximum Likelihood , 1940 .

[7]  Nir Friedman,et al.  Probabilistic Graphical Models - Principles and Techniques , 2009 .

[8]  J. Kekäläinen,et al.  Lectin staining and flow cytometry reveals female-induced sperm acrosome reaction and surface carbohydrate reorganization , 2015, Scientific Reports.

[9]  L. R. Goldberg The structure of phenotypic personality traits. , 1993, The American psychologist.

[10]  D. A. Kenny,et al.  Correlation and Causation. , 1982 .

[11]  Rina Foygel,et al.  Extended Bayesian Information Criteria for Gaussian Graphical Models , 2010, NIPS.

[12]  C. Sherbourne,et al.  The MOS 36-Item Short-Form Health Survey (SF-36) , 1992 .

[13]  Denny Borsboom,et al.  Toward a formalized account of attitudes: The Causal Attitude Network (CAN) model. , 2016, Psychological review.

[14]  A. Tellegen,et al.  An alternative "description of personality": the big-five factor structure. , 1990, Journal of personality and social psychology.

[15]  Verena D. Schmittmann,et al.  The Small World of Psychopathology , 2011, PloS one.

[16]  Arthur E. Hoerl,et al.  Ridge Regression: Biased Estimation for Nonorthogonal Problems , 2000, Technometrics.

[17]  J. Tukey,et al.  Variations of Box Plots , 1978 .

[18]  H.L.J. van der Maas,et al.  A dynamical model of general intelligence: the positive manifold of intelligence by mutualism. , 2006, Psychological review.

[19]  D. Borsboom,et al.  State of the aRt personality research: A tutorial on network analysis of personality data in R , 2015 .

[20]  Brian W. Junker,et al.  Tail-measurability in monotone latent variable models , 1997 .

[21]  Duane T. Wegener,et al.  The problem of equivalent models in applications of covariance structure analysis. , 1993, Psychological bulletin.

[22]  Laurette Dubé,et al.  An alternative to post hoc model modification in confirmatory factor analysis: The Bayesian lasso. , 2017, Psychological methods.

[23]  Klaus Nordhausen,et al.  Statistical Analysis of Network Data with R , 2015 .

[24]  Timothy R. Brick,et al.  OpenMx 2.0: Extended Structural Equation and Statistical Modeling , 2015, Psychometrika.

[25]  Denny Borsboom,et al.  Dimensions of Normal Personality as Networks in Search of Equilibrium: You Can't like Parties if you Don't like People , 2012 .

[26]  Kathleen M. Gates,et al.  Group search algorithm recovers effective connectivity maps for individuals in homogeneous and heterogeneous samples , 2012, NeuroImage.

[27]  Eric D. Kolaczyk,et al.  Statistical Analysis of Network Data , 2009 .

[28]  J. M. Digman Five robust trait dimensions: development, stability, and utility. , 1989, Journal of personality.

[29]  John J. McArdle,et al.  Regularized Structural Equation Modeling , 2015, Multivariate behavioral research.

[30]  Hongzhe Li,et al.  A SPARSE CONDITIONAL GAUSSIAN GRAPHICAL MODEL FOR ANALYSIS OF GENETICAL GENOMICS DATA. , 2011, The annals of applied statistics.

[31]  D. Borsboom,et al.  Network analysis: an integrative approach to the structure of psychopathology. , 2013, Annual review of clinical psychology.

[32]  E. Ising Beitrag zur Theorie des Ferromagnetismus , 1925 .

[33]  R. Tibshirani,et al.  On the “degrees of freedom” of the lasso , 2007, 0712.0881.

[34]  Denny Borsboom,et al.  A Network Approach to Environmental Impact in Psychotic Disorder: Brief Theoretical Framework. , 2016, Schizophrenia bulletin.

[35]  Kevin P. Murphy,et al.  Machine learning - a probabilistic perspective , 2012, Adaptive computation and machine learning series.

[36]  Leslie A. Hayduk Structural equation modeling with LISREL: essentials and advances , 1987 .

[37]  Denny Borsboom,et al.  Discovering Psychological Dynamics in Time-Series Data , 2016 .

[38]  R. Tibshirani Regression Shrinkage and Selection via the Lasso , 1996 .

[39]  Denny Borsboom,et al.  Psychometric perspectives on diagnostic systems. , 2008, Journal of clinical psychology.

[40]  M. Reckase Multidimensional Item Response Theory , 2009 .

[41]  Claudia D van Borkulo,et al.  Association of Symptom Network Structure With the Course of [corrected] Depression. , 2015, JAMA psychiatry.

[42]  Willis X Li,et al.  CORRIGENDUM: Drosophila Kdm4 demethylases in histone H3 lysine 9 demethylation and ecdysteroid signalling , 2014, Scientific Reports.

[43]  Michael I. Jordan Graphical Models , 2003 .

[44]  M. Browne,et al.  Alternative Ways of Assessing Model Fit , 1992 .

[45]  P. Bentler,et al.  Comparative fit indexes in structural models. , 1990, Psychological bulletin.

[46]  James L. Arbuckle,et al.  Full Information Estimation in the Presence of Incomplete Data , 1996 .

[47]  Denny Borsboom,et al.  Mental Disorders as Causal Systems , 2015 .

[48]  P. Costa,et al.  Personality trait structure as a human universal. , 1997, The American psychologist.

[49]  Claudia D. van Borkulo,et al.  A new method for constructing networks from binary data , 2014, Scientific Reports.

[50]  O. John,et al.  Los Cinco Grandes across cultures and ethnic groups: multitrait multimethod analyses of the Big Five in Spanish and English. , 1998, Journal of personality and social psychology.

[51]  Eiko I. Fried,et al.  Mental disorders as networks of problems: a review of recent insights , 2016, Social Psychiatry and Psychiatric Epidemiology.

[52]  K. Jöreskog A general approach to confirmatory maximum likelihood factor analysis , 1969 .

[53]  Rick H. Hoyle,et al.  Confirmatory Factor Analysis , 1983 .

[54]  M. R. Novick,et al.  Statistical Theories of Mental Test Scores. , 1971 .

[55]  Jiahua Chen,et al.  Extended Bayesian information criteria for model selection with large model spaces , 2008 .

[56]  P. Rosenbaum,et al.  Conditional Association and Unidimensionality in Monotone Latent Variable Models , 1985 .

[57]  Herbert W Marsh,et al.  Exploratory structural equation modeling: an integration of the best features of exploratory and confirmatory factor analysis. , 2014, Annual review of clinical psychology.

[58]  J. Pearl Causality: Models, Reasoning and Inference , 2000 .

[59]  Karl J. Friston,et al.  Post-hoc selection of dynamic causal models , 2012, Journal of Neuroscience Methods.

[60]  S. Wright The Method of Path Coefficients , 1934 .

[61]  Claudia D van Borkulo,et al.  The application of a network approach to Health-Related Quality of Life (HRQoL): introducing a new method for assessing HRQoL in healthy adults and cancer patients , 2015, Quality of Life Research.

[62]  Pablo A. Parrilo,et al.  Latent variable graphical model selection via convex optimization , 2010, 2010 48th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[63]  R. Krueger,et al.  Toward scientifically useful quantitative models of psychopathology: The importance of a comparative approach , 2010, Behavioral and Brain Sciences.

[64]  D. A. Kenny,et al.  Correlation and Causation , 1937, Wilmott.

[65]  D. Kaplan Structural Equation Modeling: Foundations and Extensions , 2000 .

[66]  O. John,et al.  Los Cinco Grandes across cultures and ethnic groups: multitrait multimethod analyses of the Big Five in Spanish and English. , 1998, Journal of personality and social psychology.

[67]  C. McHorney,et al.  The MOS 36‐Item Short‐Form Health Survey (SF‐36): II. Psychometric and Clinical Tests of Validity in Measuring Physical and Mental Health Constructs , 1993, Medical care.