Search

Our aim in this chapter is to discuss structural equation modeling (SEM) as it is applied in human quantitative genetics. Just as SEM is often referred to as covariance structure modeling, the application of SEM in genetics is often referred to as genetic covariance structure modeling (GCSM). Taking the seminal paper by Martin and Eaves (1977) as a starting point, the genetic analysis of covariance structures now spans a period of nearly 50 years (see Hottenga & Boomsma, 2008, for a brief history). Martin and Eaves (1977) were the first to publish an account of GCSM of twin data using Maximum Likelihood (ML) estimation based on the work of Jöreskog (1973). While Martin and Eaves developed their own program, several authors working in the field of behavior genetics and twin research realized that the user-friendly LISREL program, developed by Jöreskog and Sörbom from the 1970s onwards, could be used for genetic model fitting (Boomsma & Molenaar, 1986; Fulker, Baker, & Bock, 1983). The adoption of the LISREL program cemented the view of quantitative genetic modeling as an instance of SEM of data observed in relatives. The general aim was to obtain estimates of genetic and environmental variance components making up the phenotypic variance. The adoption of the LISREL program also encouraged applications of multivariate SEM, e.g., the common factor model, autoregressive (simplex), cross-lagged and growth curve models in genetically informative designs. It inspired approaches specific to genetics, such as Direction of Causation models, common vs. independent pathway models, and moderation models. The advent of measured genetic variables has inspired SEM for genotype-environment correlation and interaction, and intergenerational transmission). Here we introduce GCSM as it is applied in the classical twin design, and its extensions to other designs comprising larger pedigrees. We first present the basic method of exploiting familial relationships to infer the effects of unmeasured genetic and environmental factors. We explain that any SEM can be incorporated in GCSM of family data to estimate and model genetic and environmental covariance matrices. Next, we discuss several extensions that include the analysis of multi-generation data, causality, moderation of genetic influences to assess genotype-environment interaction, and the analysis of genotype-environment covariance. Finally, we consider some developments that focus on measured genetic variables in GCSM analyses and genomic SEM, which focuses on the SEM of genetic covariance matrices based on results from genetic association studies (Grotzinger et al., 2019).

This chapter introduces the reader to studying psychological dynamics operating on network models. The chapter will illustrate such dynamics using the Ising model, an undirected network model for binary variables in which nodes mutually influence one-another. First, the chapter discusses the basics of the Ising model. Second, the chapter introduces the reader to dynamics emerging from the Ising model, such as polarization and hysteresis. These dynamics will be illustrated using the example of attitude networks. Third, the chapter will illustrate how the Ising model can be used to model cross-sectional phenomena as an alternative to latent trait theories. General intelligence will be used as an example for this illustration to show how the positive manifold and block structures in correlation matrices can arise from a network implemented in the Ising model.

This chapter introduces pairwise Markov random fields (PMRFs), a class of models of which the parameters can be represented as an undirected network. In this undirected network nodes represent variables and edges represent the strength of association between two variables after conditioning on all other variables included in the model. The chapter focuses on specific classes of PMRFs often used in network psychometrics: Gaussian graphical models (GGM; a network of partial correlations) for continuous data, Ising models for binary data, and mixed graphical models (MGM) for data with different types of variables. PMRFs can be interpreted in multiple ways: the models can be used as a general statistical modeling framework, as an exploratory tool to investigate predictive relationships between variables, as a tool to generate causal hypotheses, as a causal model itself, and as an exploratory tool to uncover latent variables. The chapter concludes with an introduction to estimating PMRFs from data using the bootnet and psychonetrics packages.

Background One of the oldest and most influential theories of psychosis formation states that delusions arise in an attempt to explain unusual experiences, including perceptual aberrations. The White Noise Task by Galdos et al (2011) was developed as an experimental task to assess the tendency to attribute meaning to random perceptual stimuli: speech illusions in white noise. Studies to date have demonstrated that speech illusions as assessed with the White Noise Task are associated with a composite measure of positive symptoms in patients with psychotic disorders (Galdos et al, 2011; Catalan et al, 2014). However, findings in non-clinical samples have been inconsistent: one study found an association with a composite measure of subclinical positive symptoms, including support for a relation with familial psychosis liability (Galdos et al, 2011), whereas other studies did not find any association in non-clinical samples or only partly (Catalan et al, 2014; Rimvall et al, 2016; Pries et al, 2017). The current study aims to further examine whether speech illusions as assessed with the White Noise Task are indicative of psychosis liability and to explore specific symptomatic pathways. Methods We conducted symptom-based network analyses in Ultra-High Risk (UHR) subjects participating in the European network of national networks studying gene-environment interactions in schizophrenia project (EU-GEI, 2014; www.eu-gei.eu). Psychotic symptoms were assessed with the Brief Psychiatric Rating Scale (BPRS). Transition to clinical psychosis was assessed with the Comprehensive Assessment of At Risk Mental State (CAARMS). We used a conservative measure of speech illusions, as described in Catalan et al (2014). Results The current sample consisted of 339 UHR subjects, of which 9.1% (N=31) experienced speech illusions. Preliminary network analyses in cross-sectional baseline data showed potential pathways from speech illusions to delusional ideation, through hallucinatory experiences. We also found evidence of prospective relations between speech illusions at baseline and transition to clinical psychosis. Pathways ran via baseline psychotic symptoms and affective symptoms, as well as a ‘direct’ pathway. Discussion As far as we are aware, this is the first study combining an experimental measure of aberrant experiences with symptom-based network analysis. Although the current reported findings are preliminary and exploratory, they tentatively support a relation between speech illusions as assessed with the White Noise Task and psychosis liability. This relation may be dependent on sample composition, and not generalizable to the general population as a whole. Future studies may benefit from focusing on more detailed trajectories of both susceptibility to speech illusions and course of (sub)clinical psychotic symptom severity in subjects with increased risk for psychosis, with use of more frequent, short assessment periods and inclusion of environmental risk factors for transition to clinical disorder.

The network approach to clinical psychology is a relatively new approach and diverges on various aspects from existing models and theories. The hallmark of the theory is that there is no common cause that underlies a set of symptoms. Instead, the network approach starts out by assuming that symptoms causally interact with each other. In this chapter, we first explain the conceptualization of psychological phenomena as a network in the introduction. Second, we provide an overview of the methods that are used to construct network models from data; both Gaussian and binary data, as well as cross‐sectional and longitudinal data are covered. Third, we describe how a given network can be analyzed to uncover important symptoms in the network, to predict behavior of the network, and to compare network structures. Fourth, we discuss current state‐of‐the‐art research in clinical psychology and psychiatry, to see what these networks taught us about psychopathology. Finally, we discuss the promising prospects for clinical psychology research that the network approach has to offer and some of the challenges a researcher might face in applying this approach to clinical psychology data.

About 17% of humanity goes through an episode of major depression at some point in their lifetime. Despite the enormous societal costs of this incapacitating disorder, it is largely unknown how the likelihood of falling into a depressive episode can be assessed. Here, we show for a large group of healthy individuals and patients that the probability of an upcoming shift between a depressed and a normal state is related to elevated temporal autocorrelation, variance, and correlation between emotions in fluctuations of autorecorded emotions. These are indicators of the general phenomenon of critical slowing down, which is expected to occur when a system approaches a tipping point. Our results support the hypothesis that mood may have alternative stable states separated by tipping points, and suggest an approach for assessing the likelihood of transitions into and out of depression.

This chapter presents a commentary on representation and explanation in psychometric modelling, as discussed in the previous chapter. It explores Turkheimer’s arguments that standard psychometric techniques involve assumptions, conventions, and definitions that introduce an arbitrary component into the models used.

The International Classification of Diseases and Related Health Problems (ICD) and the Diagnostic and Statistical Manual of Mental Disorders (DSM) represent dominant approaches to diagnosis of mental disorders. However, it is unclear how these alternative systems relate to each other when taking into account the symptoms that make up the disorders. This study uses a network approach to investigate the overlap in structure between diagnostic networks pertaining to ICD-10 and DSM-IV-TR. Networks are constructed by representing individual symptoms as nodes, and connecting nodes whenever the corresponding symptoms feature as diagnostic criteria for the same mental disorder. Results indicate that, relative to the DSM-IV-TR network, the ICD-10 network contains (a) more nodes, (b) lower level of clustering, and (c) a higher level of connectivity. Both networks show features of a small world, and have similar (of “the same”) high centrality nodes. Comparison to empirical data indicates that the DSM-IV-TR network structure follows comorbidity rates more closely than the ICD-10 network structure. We conclude that, despite their apparent likeness, ICD-10 and DSM-IV-TR harbour important structural differences, and that both may be improved by matching diagnostic categories more closely to empirically determined network structures.

Network approaches to psychopathology hold that mental disorders arise from the interplay between symptoms in a network structure1, 2. In the past few years, statistical techniques that estimate networks were developed and applied to many disorders3. As empirical findings start to accumulate, the question arising is which of these findings are robust and replicable. Here we evaluate the state of psychopathological network research based on three methodological criteria: model quality, precision, and replicability.

This chapter provides a general introduction of network modeling in psychometrics. The chapter starts with an introduction to the statistical model formulation of pairwise Markov random fields (PMRF), followed by an introduction of the PMRF suitable for binary data: the Ising model. The Ising model is a model used in ferromagnetism to explain phase transitions in a field of particles. Following the description of the Ising model in statistical physics, the chapter continues to show that the Ising model is closely related to models used in psychometrics. The Ising model can be shown to be equivalent to certain kinds of logistic regression models, loglinear models and multi-dimensional item response theory (MIRT) models. The equivalence between the Ising model and the MIRT model puts standard psychometrics in a new light and leads to a strikingly different interpretation of well-known latent variable models. The chapter gives an overview of methods that can be used to estimate the Ising model, and concludes with a discussion on the interpretation of latent variables given the equivalence between the Ising model and MIRT., In Irwing, P., Hughes, D., and Booth, T. (2018). The Wiley Handbook of Psychometric Testing, 2 Volume Set: A Multidisciplinary Reference on Survey, Scale and Test Development. New York: Wiley

Among the topics discussed in the comments, one idea appeared to be supported by most commenters: when personality trait scores are related to possible outcome variables (or possible causal factors, for that matter), scale-level analyses should be supplemented by item-level analyses. This could help to corroborate causal inferences, refine interpretations, rule out measurement/construct overlaps and/or lead to new discoveries. This suggestion is consistent with recent evidence regarding single items often reflecting unique personality characteristics (“nuances”) with trait-like properties. Future work could focus on improving item properties and delineating a useful set of nuances.

Mõttus gives the impression that composites, as well as other models in which traits are a result rather than a cause of their indicators, require “emergent properties” to have causal power. We argue that this is not necessary; composites can be considered causally relevant by themselves when they mediate the relation between their constituents and the outcome variable.

Psychometrics is a scientific discipline concerned with the construction of measurement models for psychological data. In these models, a theoretical construct (e.g., intelligence) is systematically coordinated with observables (e.g., IQ scores). This is often done through latent variable models, which represent the construct of interest as a latent variable that acts as the common determinant of a set of test scores. Important psychometric questions include (1) how much information about the latent variable is contained in the data (measurement precision), (2) whether the test scores indeed measure the intended construct (validity), and (3) to what extent the test scores function in the same way in different groups (measurement invariance). Recent developments have focused on extending the basic latent variable model for more complex research designs and on implementing psychometric models in freely available software.

What is the nature of mental disorders such as major depression and panic disorder? Are mental disorders analogous to tumors, in that they exist as separate entities somewhere in people's minds? Do mental disorders cause symptoms such as insomnia and fatigue? Until very recently, it was exactly this sort of thinking that (implicitly) permeated many, if not all, research paradigms in clinical psychology and psychiatry. However, in recent years, a novel approach has been advocated (i.e., the network perspective), in which mental disorders are not conceived of as entities that have a separate existence from their respective symptoms. Instead, mental disorders are hypothesized to be networks of symptoms that directly influence one another. So, for example, from a network perspective, insomnia and fatigue are not caused by the same underlying disorder (i.e., major depression) but causally influence one another (i.e., insomnia → fatigue). A disorder, then, develops because of such direct relations between symptoms in which positive feedback mechanisms (i.e., vicious circles) are present: for example, insomnia → fatigue → feelings of guilt → insomnia. These feedback mechanisms may propel the aggravation of one's condition and make a person end up in, for example, a full-fledged depressive episode. In this contribution, we elaborate on network perspectives on the nature of mental disorders as well as their implications for our outlook on diagnosis and comorbidity.

Research on extrasensory perception (ESP) or psi is contentious and highly polarized. On the one hand, its proponents believe that evidence for psi is overwhelming, and they support their case with a seemingly impressive series of experiments and meta-analyses. On the other hand, psi skeptics believe that the phenomenon does not exist, and the claimed statistical support is entirely spurious. We are firmly in the camp of the skeptics. However, the main goal of this chapter is not to single out and critique individual experiments on psi. Instead, we wish to highlight the many positive consequences that psi research has had on traditional empirical research—an influence that we hope and expect will continue in the future

Adrianus Dingeman de Groot (1914-2006) was one of the most influential Dutch psychologists. He became famous for his work "Thought and Choice in Chess", but his main contribution was methodological — De Groot co-founded the Department of Psychological Methods at the University of Amsterdam (together with R. F. van Naerssen), founded one of the leading testing and assessment companies (CITO), and wrote the monograph "Methodology" that centers on the empirical-scientific cycle: observation-induction-deduction-testing-evaluation. Here we translate one of De Groot's early articles, published in 1956 in the Dutch journal Nederlands Tijdschrift voor de Psychologie en Haar Grensgebieden. This article is more topical now than it was almost 60 years ago. De Groot stresses the difference between exploratory and confirmatory ("hypothesis testing") research and argues that statistical inference is only sensible for the latter: "One ‘is allowed’ to apply statistical tests in exploratory research, just as long as one realizes that they do not have evidential impact". De Groot may have also been one of the first psychologists to argue explicitly for preregistration of experiments and the associated plan of statistical analysis. The appendix provides annotations that connect De Groot's arguments to the current-day debate on transparency and reproducibility in psychological science.

We welcome the recommendations suggested by Asendorpf et al. Their proposed changes will undoubtedly improve psychology as an academic discipline. However, our current knowledge is based on past research. We therefore have an obligation to ‘dwell on the past’; that is, to investigate the veracity of previously published findings—particularly those featured in course materials and popular science books. We discuss some examples of staple ‘facts’ in psychology that are actually no more than hypotheses with rather weak empirical support and suggest various ways to remedy this situation.

Lee (2012) proposes that personality research should utilise recent theories of causality. Although we agree that such theories are important, we also note that their empirical application has not been very successful to date. The reason may be that psychological systems are frequently characterised by feedback, nonlinearity and individual differences in causal structure. Such features do not preclude the application of causal modelling but do limit the usefulness of the approach for the analysis of typical personality data. To adequately investigate personality, intensive time series of repeated measurements are needed.

Does psi exist? D. J. Bem (2011) conducted 9 studies with over 1,000 participants in an attempt to demonstrate that future events retroactively affect people's responses. Here we discuss several limitations of Bem's experiments on psi; in particular, we show that the data analysis was partly exploratory and that one-sided p values may overstate the statistical evidence against the null hypothesis. We reanalyze Bem's data with a default Bayesian t test and show that the evidence for psi is weak to nonexistent. We argue that in order to convince a skeptical audience of a controversial claim, one needs to conduct strictly confirmatory studies and analyze the results with statistical tests that are conservative rather than liberal. We conclude that Bem's p values do not indicate evidence in favor of precognition; instead, they indicate that experimental psychologists need to change the way they conduct their experiments and analyze their data.

The missing heritability problem is pervasive and Johnson, Penke and Spinath (2011) present a number of compelling reasons for its existence. In this comment, we present another reason for the apparent discrepancy between heritability estimates and gene‐hunting results in psychopathological research: if syndromes are networks of causally related symptoms in which both symptoms and relations between them are driven by different sets of genetic polymorphisms, then gene hunting based on a phenotypic sumscore might be ill‐advised because it will only capture genetic variance shared among those symptoms and their relations.

Network analysis represents a novel theoretical approach to personality. Network approaches motivate alternative ways of analyzing data, and suggest new ways of modeling and simulating personality processes. In the present paper, we provide an overview of network analysis strategies as they apply to personality data. We discuss different ways to construct networks from typical personality data, show how to compute and interpret important measures of centrality and clustering, and illustrate how one can simulate on networks to mimic personality processes. All analyses are illustrated using a data set on the commonly used HEXACO questionnaire using elementary R-code that readers may easily adapt to apply to their own data.

Because indirect measures of personality self–concepts such as the Implicit Association Test (IAT) allow tapping into automatic processes, they can offer advantages over self–report measures. However, prior investigations have led to mixed results regarding the validity of indirect measures of conscientiousness. We suggest that these results might be due to a failure to consider the different facets of conscientiousness. These facets are of crucial importance because they are associated differentially with other psychobiological constructs and they are also characterized by different mechanisms. Therefore, focusing on facets while developing indirect measures of conscientiousness may improve the validity of such measures. In Study 1, we conducted a psycholexical investigation to develop one IAT for each conscientiousness facet. In Study 2, we examined the convergent and discriminant validities of each facet IAT in relation to self–report measures, peer–report measures and self–report behavioural indicators, and we investigated differential associations of the conscientiousness facets with working memory capacity and self–control. We employed network analysis as a novel approach to elucidate differential relationships involving personality facets. The results corroborated the convergent and discriminant validity of the conscientiousness facet IATs with self–reports and showed that the conscientiousness facets were differentially associated with working memory capacity and with self–control. Copyright © 2015 European Association of Personality Psychology

IntroductionReproducibility is a defining feature of science, but the extent to which it characterizes current research is unknown. Scientific claims should not gain credence because of the status or authority of their originator but by the replicability of their supporting evidence. Even research of exemplary quality may have irreproducible empirical findings because of random or systematic error.RationaleThere is concern about the rate and predictors of reproducibility, but limited evidence. Potentially problematic practices include selective reporting, selective analysis, and insufficient specification of the conditions necessary or sufficient to obtain the results. Direct replication is the attempt to recreate the conditions believed sufficient for obtaining a previously observed finding and is the means of establishing reproducibility of a finding with new data. We conducted a large-scale, collaborative effort to obtain an initial estimate of the reproducibility of psychological science.ResultsWe conducted replications of 100 experimental and correlational studies published in three psychology journals using high-powered designs and original materials when available. There is no single standard for evaluating replication success. Here, we evaluated reproducibility using significance and P values, effect sizes, subjective assessments of replication teams, and meta-analysis of effect sizes. The mean effect size (r) of the replication effects (Mr = 0.197, SD = 0.257) was half the magnitude of the mean effect size of the original effects (Mr = 0.403, SD = 0.188), representing a substantial decline. Ninety-seven percent of original studies had significant results (P < .05). Thirty-six percent of replications had significant results; 47% of original effect sizes were in the 95% confidence interval of the replication effect size; 39% of effects were subjectively rated to have replicated the original result; and if no bias in original results is assumed, combining original and replication results left 68% with statistically significant effects. Correlational tests suggest that replication success was better predicted by the strength of original evidence than by characteristics of the original and replication teams.ConclusionNo single indicator sufficiently describes replication success, and the five indicators examined here are not the only ways to evaluate reproducibility. Nonetheless, collectively these results offer a clear conclusion: A large portion of replications produced weaker evidence for the original findings despite using materials provided by the original authors, review in advance for methodological fidelity, and high statistical power to detect the original effect sizes. Moreover, correlational evidence is consistent with the conclusion that variation in the strength of initial evidence (such as original P value) was more predictive of replication success than variation in the characteristics of the teams conducting the research (such as experience and expertise). The latter factors certainly can influence replication success, but they did not appear to do so here. Reproducibility is not well understood because the incentives for individual scientists prioritize novelty over replication. Innovation is the engine of discovery and is vital for a productive, effective scientific enterprise. However, innovative ideas become old news fast. Journal reviewers and editors may dismiss a new test of a published idea as unoriginal. The claim that “we already know this” belies the uncertainty of scientific evidence. Innovation points out paths that are possible; replication points out paths that are likely; progress relies on both. Replication can increase certainty when findings are reproduced and promote innovation when they are not. This project provides accumulating evidence for many findings in psychological research and suggests that there is still more work to do to verify whether we know what we think we know.