Researchers routinely face the problem of inferring causal relationships from large amounts of data, sometimes involving hundreds of variables. Often, it is the causal relationships between "latent" (unmeasured) variables that are of primary interest. The problem is how causal relationships between unmeasured variables can be inferred from measured data. For example, naval manpower researchers have been asked to infer the causal relations among psychological traits such as job satisfaction and job challenge from a data base in which neither trait (...) is measured directly, but in which answers to interview questions are plausibly associated with each trait. By combining background knowledge with an algorithm that searches for causal structure among the unobserved variables, we have created a tool that can reliably extract useful causal information about latent variables from large data bases. In what follows we describe the class of causal models to which our.. (shrink)

Cramer et al. present an original and interesting network perspective on comorbidity and contrast this perspective with a more traditional interpretation of comorbidity in terms of latent variable theory. My commentary focuses on the relationship between the two perspectives; that is, it aims to qualify the presumed contrast between interpretations in terms of networks and latent variables.

We consider the use of interventions for resolving a problem of unidentified statistical models. The leading examples are from latent variable modelling, an influential statistical tool in the social sciences. We first explain the problem of statistical identifiability and contrast it with the identifiability of causal models. We then draw a parallel between the latent variable models and Bayesian networks with hidden nodes. This allows us to clarify the use of interventions for dealing (...) with unidentified statistical models. We end by discussing the philosophical and methodological import of our result. (shrink)

Effective feature representation is the key to success of machine learning applications. Recently, many feature learning models have been proposed. Among these models, the Gaussian process latent variable model for nonlinear feature learning has received much attention because of its superior performance. However, most of the existing GPLVMs are mainly designed for classification and regression tasks, thus cannot be used in data clustering task. To address this issue and extend the application scope, this paper proposes a (...) novel GPLVM for clustering. Specifically, by combining GPLVM with the subspace clustering method, our C-GPLVM can obtain more representative latent variable for clustering. Moreover, it can directly predict the new samples by introducing a back constraint in the model, thus being more suitable for big data learning tasks such as analysis of chaotic time series and so on. In the experiment, we compare it with the related GPLVMs and clustering algorithms. The experimental results show that the proposed model not only inherits the feature learning ability of GPLVM but also has superior clustering accuracy. (shrink)

Linear structural equation models with latent (unmeasured) variables are used widely in sociology, psychometrics, and political science. When such models have a unidimensional..

We describe anytime search procedures that (1) find disjoint subsets of recorded variables for which the members of each subset are d-separated by a single common unrecorded cause, if such exists; (2) return information about the causal relations among the latent factors so identified. We prove the procedure is point-wise consistent assuming (a) the causal relations can be represented by a directed acyclic graph (DAG) satisfying the Markov Assumption and the Faithfulness Assumption; (b) unrecorded variables are not caused by (...) recorded variables; and (c) dependencies are linear. We compare the procedure with standard approaches over a variety of simulated structures and sample sizes, and illustrate its practical value with brief studies of social science data sets. Finally, we consider generalizations for non-linear systems. Keywords: latent variable models, causality, graphical models.. (shrink)

Bayesian approaches for estimating multilevel latent variable models can be beneficial in small samples. Prior distributions can be used to overcome small sample problems, for example, when priors that increase the accuracy of estimation are chosen. This article discusses two different but not mutually exclusive approaches for specifying priors. Both approaches aim at stabilizing estimators in such a way that the Mean Squared Error of the estimator of the between-group slope will be small. In the first approach, (...) the MSE is decreased by specifying a slightly informative prior for the group-level variance of the predictor variable, whereas in the second approach, the decrease is achieved directly by using a slightly informative prior for the slope. Mathematical and graphical inspections suggest that both approaches can be effective for reducing the MSE in small samples, thus rendering them attractive in these situations. The article also discusses how these approaches can be implemented in Mplus. (shrink)

Emotion dysregulation (ED) is a vulnerability factor for affective disorders that may originate from deficits in cognitive control (CC). Although measures of ED are often designed to assess trait-like tendencies, the extent to which such measures capture a time-varying (TV) or state-like construct versus a time-invariant (TI) or trait-like personality characteristic is unclear. The link between the TV and TI components of ED and CC is also unclear. In a 6-wave, 5-month longitudinal study, community participants (n = 1281) completed the (...) Difficulties in Emotion Regulation Scale (DERS-16), a commonly used measure of ED and measures of CC. A latent variable (trait-state-occasion) model showed that the proportion of TI factor variance (.80) was greater than the TV factor variance (.19). Although TV factor stability was significant, the coefficients were small in magnitude. Furthermore, regression weights for the ED TI factor (average β = −.62) were significant and larger than those for the TV factor (average β = −.10) in predicting latent CC at each of the six-time points. These findings suggest that ED, as assessed by the DERS-16, is largely TI and this TI component is more strongly linked to CC than the TV component. (shrink)

A Bayesian network consists of two distinct parts: a directed acyclic graph (DAG or belief-network structure) and a set of parameters for the DAG. The DAG in a Bayesian network can be used to represent both causal hypotheses and sets of probability distributions. Under the causal interpretation, a DAG represents the causal relations in a given population with a set of vertices V when there is an edge from A to B if and only if A is a direct cause (...) of B relative to V. (We adopt the convention that sets of variables are capitalized and boldfaced, and individual variables are capitalized and italicized.) Under the statistical interpretation a DAG G can be taken to represent a set of all distributions all of which share a set of conditional independence relations that are entailed by satisfying a local directed Markov property (defined below). (shrink)

Peter Spirtes. Discovering Causal Relations Among Latent Variables in Directed Acyclical Graphical Models.

BackgroundTo investigate the factors related to approval after review by an Institutional Review Board, the structure equation model was used to analyze the latent variables ‘investigators’, ‘vulnerability’ and ‘review process’ for 221 proposals submitted to our IRB.MethodsThe vulnerability factor included vulnerable cases, and studies that involved drug tests and genetic analyses. The principal investigator factor included the license level of the PI and whether they belonged to our institution. The review factor included administration time, total review time, and revision (...) frequency. The revision frequency and total review time influenced the efficiency of review.ResultsThe latent variable of reviewing was the most important factor mediating the PIs and vulnerability to IRB review approval. The local PIs moderated with genetic study and revision frequency had an impact on the review process and mediated non-approval.ConclusionsBetter guidance of the investigators and reviewers might improve the efficiency with which IRBs function. (shrink)

Peter Spirtes and Thomas Verma. Equivalence of Causal Models with Latent Variables.

We present an algorithm to infer causal relations between a set of measured variables on the basis of experiments on these variables. The algorithm assumes that the causal relations are linear, but is otherwise completely general: It provides consistent estimates when the true causal structure contains feedback loops and latent variables, while the experiments can involve surgical or `soft' interventions on one or multiple variables at a time. The algorithm is `online' in the sense that it combines the results (...) from any set of available experiments, can incorporate background knowledge and resolves conflicts that arise from combining results from different experiments. In addition we provide a necessary and sufficient condition that determines when the algorithm can uniquely return the true graph, and can be used to select the next best experiment until this condition is satisfied. We demonstrate the method by applying it to simulated data and the flow cytometry data of Sachs et al. (shrink)

Based on the data of four periods of CLHLS, the latent variable growth model was applied to 2344 older adults who completed four follow-up surveys, to study the trajectory of leisure activities and cognitive ability and explore the relationship between leisure activities and cognitive ability of older adults. The results showed that: leisure activities and cognitive ability of older adults showed a non-linear downward trend; leisure activities significantly and positively predicted the cognitive ability of older adults at every (...) time point; the initial level of leisure activity positively predicted the initial level of cognitive ability but negatively predicted the rate of cognitive decline; In addition, cognitive activities had a greater effect on cognitive ability than non-exercise physical activities; the rate of decline of leisure activities also significantly and positively predicted the rate of decline of cognitive ability; cross-lagged regression analysis further suggested the overall positive predictive effect of leisure activity on cognitive ability; overall, education level had a significant contribution to cognitive ability, and the higher the education level, the slower the decline of cognitive ability; and smoking could promote cognitive ability in older adults and no significant effect was found between alcohol drinking and cognitive ability. Accordingly, the government should encourage older adults to do more leisure activities, especially the cognitive activity, to effectively prevent cognitive decline. (shrink)

First, we question whether Cramer et al.'s proposed network model can provide a viable scientific foundation for investigating comorbidity without invoking latent variables in some form. Second, the authors' claim that the network perspective is radically different from a latent variable perspective rests upon an undemonstrated premise. Without being demonstrated, we think the premise is potentially misleading.

Cramer et al.'s critique of latent variables implicitly advocates a type of scientific anti-realism which can be extended to many dispositional constructs in scientific psychology. However, generalizing Cramer et al.'s network model in this way raises concerns about its applicability to psychopathology. The model could be improved by articulating why a given cluster of symptoms should be considered disordered.

It is well known that there may be many causal explanations that are consistent with a given set of data. Recent work has been done to represent the common aspects of these explanations into one representation. In this paper, we address what is less well known: how do the relationships common to every causal explanation among the observed variables of some DAG process change in the presence of latent variables? Ancestral graphs provide a class of graphs that can encode (...) conditional independence relations that arise in DAG models with latent and selection variables. In this paper we present a set of orientation rules that construct the Markov equivalence class representative for ancestral graphs, given a member of the equivalence class. These rules are sound and complete. We also show that when the equivalence class includes a DAG, the equivalence class representative is the essential graph for the said DAG. (shrink)

The ability to generate options for action is crucial for everyday life decision‐making. In this article, we propose and test a model of the cognitive underpinnings of option generation in everyday life situations. We carried out a laboratory study using measures of a wide range of cognitive functions and asked participants (N = 157) to generate options for actions for different everyday life decision‐making scenarios. The results of a latent variable analysis show that the cognitive underpinnings of option (...) generation are consistent across different everyday life situations and, hence, option generation can be conceptualized as a general construct. Moreover, the results of a confirmatory factor analysis reveal that, when controlling for the shared variance among the cognitive processes assessed, verbal fluency, working memory capacity, ideation fluency, and processing speed predicted option generation. These findings suggest that option generation in everyday life situations can be distinguished from other cognitive constructs, such as divergent thinking (in terms of ideas’ originality) and long‐term memory. (shrink)

Different directed acyclic graphs may be Markov equivalent in the sense that they entail the same conditional independence relations among the observed variables. Chickering provided a transformational characterization of Markov equivalence for DAGs, which is useful in deriving properties shared by Markov equivalent DAGs, and, with certain generalization, is needed to prove the asymptotic correctness of a search procedure over Markov equivalence classes, known as the GES algorithm. For DAG models with latent variables, maximal ancestral graphs provide a (...) neat representation that facilitates model search. However, no transformational characterization -- analogous to Chickering's -- of Markov equivalent MAGs is yet available. This paper establishes such a characterization for directed MAGs, which we expect will have similar uses as it does for DAGs. (shrink)

Different directed acyclic graphs may be Markov equivalent in the sense that they entail the same conditional indepen- dence relations among the observed variables. Meek characterizes Markov equiva- lence classes for DAGs by presenting a set of orientation rules that can correctly identify all arrow orienta- tions shared by all DAGs in a Markov equiv- alence class, given a member of that class. For DAG models with latent variables, maxi- mal ancestral graphs provide a neat representation that facilitates (...) model search. Earlier work has identified a set of orientation rules sufficient to con- struct all arrowheads common to a Markov equivalence class of MAGs. In this paper, we provide extra rules sufficient to construct all common tails as well. We end up with a set of orientation rules sound and complete for identifying commonalities across a Markov equivalence class of MAGs, which is partic- ularly useful for causal inference. (shrink)

Learning equivalence classes of acyclic models with latent and selection variables from multiple datasets with overlapping variables is discussed. The problem of inferring the presence of latent variables, their relation to the observables, and the relation among themselves, is considered. A different approach for identifying causal structures, one that results in much simpler equivalence classes, is provided. It is found that the computational cost is much higher than the procedure implemented, but if datasets are individually of modest (...) dimensionality, it might be doable in practice. From the point of view of search algorithms for optimizing structure, much of the machinery of combinatorial optimization could optimize the penalized composite likelihood score by enforcing constraints such that the independence models over different subsets of variables agree on the overlapping sets. (shrink)

Working speed as a latent variable reflects a respondent’s efficiency to apply a specific skill, or a piece of knowledge to solve a problem. In this study, the common assumption of many response time models is relaxed in which respondents work with a constant speed across all test items. It is more likely that respondents work with different speed levels across items, in specific when these items measure different dimensions of ability in a multidimensional test. Multiple speed (...) factors are used to model the speed process by allowing speed to vary across different domains of ability. A joint model for multidimensional abilities and multifactor speed is proposed. Real response time data are analyzed with an exploratory factor analysis as an example to uncover the complex structure of working speed. The feasibility of the proposed model is examined using simulation data. An empirical example with responses and response times is presented to illustrate the proposed model’s applicability and rationality. (shrink)

The wanton dissemination of network pseudohealth information has brought great harm to people’s health, life, and property. It is important to detect and identify network pseudohealth information. Based on this, this paper defines the concepts of pseudohealth information, data block, and data block integration, designs an architecture that combines the latent Dirichlet allocation algorithm and data block update integration, and proposes the combination algorithm model. In addition, crawler technology is used to crawl the pseudohealth information transmitted on the Sina (...) Weibo platform during the “epidemic situation” from February to March 2020 for the simulation test on the experimental case dataset. The research results show that the LDA model can deeply mine the semantic information of network pseudohealth information, obtain the features of document-topic distribution, and classify and train topic features as input variables; the dataset partitioning method can effectively block data according to the text attributes and class labels of network pseudohealth information and can accurately classify and integrate the block data through the data block reintegration method; and considering that the combination model has certain limitations on the detection of network pseudohealth information, the support vector machine model can extract the granularity content of data blocks in pseudohealth information in real time, thus greatly improving the recognition performance of the combination model. (shrink)

Background: The three-dimensional model of nurses’ moral sensitivity has typically been studied using a variable-centered rather than a person-centered approach, preventing a more complete understanding of how these forms of moral sensitivity are expressed as a whole. Latent profile analysis is a person-centered approach that classifies individuals from a heterogeneous population into homogeneous subgroups, helping identify how different subpopulations of nurses use distinct combinations of different moral sensitivities to affect their service behaviors. Objective: Latent profile analysis was (...) used to identify three distinct profiles of nurses’ moral sensitivity. Associations of the profiles with service behaviors were then examined. Methods: Five hundred twenty-five nurses from three tertiary hospitals in China were investigated with Moral Sensitivity Questionnaire and Nurses’ Service Behavior Scale. Latent profile analysis was used to analyze the data. Ethical considerations: Approval was obtained from the Ethics committee for biomedical research of Medical College, the Hebei University of Engineering. Results: A three-profile moral sensitivity model provided the best fit to the data. The resulting profiles were low moral sensitivity, moderate moral sensitivity, and high moral sensitivity. There were significant differences in service behaviors among different profiles of moral sensitivity. Conclusion: The results provide a new and expanded view of nurses’ moral sensitivity, which may be used to monitor nurses’ service behaviors comprehensively and to evaluate nursing ethics management strategies. (shrink)

This study aimed to examine the number of latent classes of criminal social identity that exist among male recidivistic prisoners. Latent class analysis was used to identify homogeneous groups of criminal social identity. Multinomial logistic regression was used to interpret the nature of the latent classes, or groups, by estimating the associationsto number of police arrests, recidivism, and violent offending while controlling for current age. The best fitting latent class model was a five-class solution: ‘High criminal (...) social identity’, ‘High Centrality, Moderate Affect, Low Ties’, ‘Low Centrality, Moderate Affect, High Ties’,‘Low Cognitive, High Affect, Low Ties’, and ‘Low criminal social identity’. Each of the latent classes was predicted by differing external variables. Criminal social identity is best explained by five homogenous classes that display qualitative and quantitative differences. (shrink)

The dual-continua model of mental health provides a contemporary framework for conceptualising and operationalising mental health. According to this model, mental health is distinct from but related to mental illness, and not the opposite or merely the absence of psychopathology symptoms. To examine the validity of the dual-continua model, previous studies have either applied variable-based analysis such as confirmatory factor analysis, or used predetermined cut-off points for subgroup division. The present study extends this contribution by subjecting data from an (...) African sample to both CFA and latent class analysis to test the dual-continua model in Africa. We applied CFA separately for the Mental Health Continuum—Short Form and Patient Health Questionnaire—9 ; and LCA on combined item responses. College students from Ghana, Kenya, Mozambique, and South Africa completed the MHC-SF and PHQ-9. With minor modifications to the measurement models, the CFA results of this study confirm the three-factor structure of the MHC-SF, and a unidimensional solution for the PHQ-9. LCA results show the presence of three distinct latent classes: languishing with moderate endorsement of depressive symptoms, flourishing with low endorsement of depressive symptoms, and moderate mental health with high endorsement of depressive symptoms. These findings further contribute to affirming the evidence for the dual-continua model of mental health, with implications for the assessment of mental health, to inform policy, practise, and future research in community and clinical settings in Africa. (shrink)

The network approach to psychopathology is becoming increasingly popular. The motivation for this approach is to provide a replacement for the problematic common cause perspective and the associated latent variable model, where symptoms are taken to be mere effects of a common cause (the disorder itself). The idea is that the latent variable model is plausible for medical diseases, but unrealistic for mental disorders, which should rather be conceptualized as networks of directly interacting symptoms. We argue (...) that this rationale for the network approach is misguided. Latent variable (or common cause) models are not inherently problematic, and there is not even a clear boundary where network models end and latent variable (or common cause) models begin. We also argue that focusing on this contrast has led to an unrealistic view of testing and finding support for the network approach, as well as an oversimplified picture of the relationship between medical diseases and mental disorders. As an alternative, we point out more essential contrasts, such as the contrast between dynamic and static modeling approaches, that can provide a better framework for conceptualizing mental disorders. Finally, we discuss several topics and open problems that need to be addressed in order to make the network approach more concrete and to move the field of psychological network research forward. (shrink)

Multitrait-multimethod (MTMM) analysis is one of the most frequently employed methods to examine the validity of psychological measures. Confirmatory factor analysis (CFA) is a commonly used analytic tool for examining MTMM data through the specification of trait and method latent variables. Most contemporary CFA-MTMM models either do not allow estimating correlations between the trait and method factors or they are restricted to linear trait-method relationships. There is no theoretical reason why trait and method relationships should always be linear, (...) and quadratic relationships are frequently proposed in the social sciences. In this article, we present two approaches for examining quadratic relations between traits and methods through extended latent difference and latent means CFA-MTMM models (Pohl et al., 2008; Pohl and Steyer, 2010). An application of the new approaches to a multi-rater study of the nine inattention symptoms of attention-deficit/hyperactivity disorder in children (N = 752) and the results of a Monte Carlo study to test the applicability of the models under a variety of data conditions are described. (shrink)

The pivotal problem of comorbidity research lies in the psychometric foundation it rests on, that is, latent variable theory, in which a mental disorder is viewed as a latent variable that causes a constellation of symptoms. From this perspective, comorbidity is a (bi)directional relationship between multiple latent variables. We argue that such a latent variable perspective encounters serious problems in the study of comorbidity, and offer a radically different conceptualization in terms of a (...) network approach, where comorbidity is hypothesized to arise from direct relations between symptoms of multiple disorders. We propose a method to visualize comorbidity networks and, based on an empirical network for major depression and generalized anxiety, we argue that this approach generates realistic hypotheses about pathways to comorbidity, overlapping symptoms, and diagnostic boundaries, that are not naturally accommodated by latent variable models: Some pathways to comorbidity through the symptom space are more likely than others; those pathways generally have the same direction (i.e., from symptoms of one disorder to symptoms of the other); overlapping symptoms play an important role in comorbidity; and boundaries between diagnostic categories are necessarily fuzzy. (shrink)

We discuss a recent approach to investigating cognitive control, which has the potential to deal with some of the challenges inherent in this endeavour. In a model-based approach, the researcher defines a formal, computational model that performs the task at hand and whose performance matches that of a research participant. The internal variables in such a model might then be taken as proxies for latent variables computed in the brain. We discuss the potential advantages of such an approach for (...) the study of the neural underpinnings of cognitive control and its pitfalls, and we make explicit the assumptions underlying the interpretation of data obtained using this approach. (shrink)

An unresolved issue in the occupational health literature that is of both theoretical and practical importance is whether interpersonal conflicts, aggression and bullying at work are distinct or overlapping phenomena for exposed workers. In this study, we addressed this question empirically by employing a Latent Class (LC) analysis using cross-industry data from 6,175 Belgian workers. We found that a two-factor solution with a conflict-aggression factor and a bullying factor had the best fit. Employees with low exposure to workplace conflicts-aggression (...) and bullying perceived the phenomena as mostly overlapping. Reversely, employees who were exposed more frequently to the phenomena perceived them as more distinct - especially so for workplace bullying. Conflicts-aggression and bullying seem to be perceived as separate phenomena given their distinctive relationships with criterion variables in the domain of well-being and strain. These findings entail that a simple unifying approach or a single label for the three phenomena is not appropriate, at least from a measurement point of view and from the different perspectives of those exposed. Our results have important implications for the theoretical understanding of the concepts of interpersonal conflicts, aggression and bullying, and for practitioners who have to assist those involved with how to handle these problems and who have to develop legal as well as internal policies for the prevention and management of these issues at the workplace. (shrink)

Using a latent variable modelling strategy we study individual differences in patterns of answers to the selection task and to the truth table task. Specifically we investigate the prediction of mental model theory according to which the individual tendency to select the false consequent card (in the selection task) is negatively correlated with the tendency to judge the false antecedent cases as irrelevant (in the truth table task). We fit a psychometric model to two large samples ( N (...) = 486, twice), and find no evidence for this negative correlation. We examine which of the assumptions of the model theory must be amended to accommodate our findings. (shrink)

Cramer et al. articulate a novel perspective on comorbidity. However, their network models must be compared with more parsimonious latent variable models before conclusions can be drawn about network models as plausible accounts of comorbidity. Latent variable models have proven generative in studying psychopathology and its external correlates, and we doubt network models will prove as useful for psychopathology research.

Resumen: El presente artículo se propone examinar la clausura del concepto benjaminiano de aura como noción válida para pensar la experiencia estética contemporánea. En este sentido, un primer objetivo consiste en rehabilitar tal concepto, cotejando su definición en el famoso ensayo sobre la reproductibilidad técnica con las diversas formulaciones que el mismo Benjamin elabora al respecto en otros ensayos, en los que la gravitación del aura se desplaza desde una cualidad objetiva, anidada en la obra misma, hacia una facultad perceptual (...) y memoriosa que organiza su experiencia histórica. A partir de lo anterior, un segundo objetivo consiste en pesquisar las huellas de un presunto modelo de historiografía del arte que Benjamin esboza en una carta dirigida a Florens Christian Rang y que afina en su ensayo sobre Eduard Fuchs. Establecidos los lineamientos de este modelo, el artículo concluye que el concepto de aura no remite tanto a una datación de origen de la obra de arte, circunscribiendo exclusivamente sus condiciones de producción, sino a las coordenadas variables en las que cada época recupera para sí una obra de arte determinada. Esta recuperación, imantada por el mecanismo de las correspondances, donde la singularidad de una obra de arte hace sistema con una situación histórica determinada, permite comprender finalmente el aura como un modo de experiencia de las imágenes del arte.: The following work attempts to examine Walter Benjamin’s concept of aura as a valid notion for thinking about contemporary aesthetic experience. In this regard, our first goal is to rehabilitate this concept, comparing its definition in the famous essay on technical reproducibility with other formulations developed by Benjamin in essays such as a “A short history of photography”, “The storyteller”, and “On some motifs in Baudelaire”, in which aura is not understood as an objective quality pertaining to the work of art itself, but as the perceptive and mnemonic faculty organizing its historical experience. Our second goal is to locate the traces of a model for the historiography art, which Benjamin outlines in a letter written to Florens Christian Rang and which he refines in his essay on Eduard Fuchs. Within this context, the article concludes that the concept of aura does not refer to a work of art’s time of origin, but to the variable coordinates that allow each epoch to make its own experience of that work of art. Through the mechanism of correspondences, by which a work of art’s singularity matches with a specific historical situation, we are able understand aura as a mode of experience of the images of art. (shrink)

A hypnotic induction produces different patterns of spontaneous experiences across individuals. The magnitude and characteristics of these responses covary moderately with hypnotic suggestibility, but also differ within levels of hypnotic suggestibility. This study sought to identify discrete phenomenological profiles in response to a hypnotic induction and assess whether experiential variability among highly suggestible individuals matches the phenomenological profiles predicted by dissociative typological models of high hypnotic suggestibility. Phenomenological state scores indexed in reference to a resting epoch during hypnosis were (...) submitted to a latent profile analysis. The profiles in the derived four-class solution differed in multiple experiential dimensions and hypnotic suggestibility. Highly suggestible individuals were distributed across two classes that exhibited response patterns suggesting an inward attention subtype and a dissociative subtype. These results provide support for dissociative typological models of high hypnotic suggestibility and indicate that highly suggestible individuals do not display a uniform response to a hypnotic induction. (shrink)

In this paper we deal firstly with epistemological foundations of the process of operationalization in general and the character of correspondence rules in particular. After this we discuss the theoretical foundation of a scale for measuring work motivation. We explicate three different approaches, which can be used as a theoretical background for this scale. As a next step we specify and test different measurement theories relating the observable and the latent variables and compare their suitability. The sample used is (...) a representative sample of the West-German population in 1980. Finally we test the stability of the best model in different age groups. (shrink)

The purpose of the present study was to profile high school students’ achievement as a function of their demographic characteristics, parent attributes, and school behaviors. Students were nested within schools in the Saudi Arabia Kingdom. Out of a large sample of 500k, participants involved 3 random samples of 2,000 students measured during the years 2016, 2017, and 2018. Randomization was conducted at the student level to ensure that all school units will be represented and at their respective frequency. Students were (...) nested within 50 high schools. We adopted the multilevel latent profile analysis protocol put forth by Schmiege et al. and Mäkikangas et al. that account for nested data and tested latent class structure invariance over time. Results pointed to the presence of a 4-profile solution based on BIC, the Bayes factor, and several information criteria put forth by Masyn. Latent profile separation was mostly guided by parents’ education and the number of student absences. Two models tested whether the proportions of level 1 profiles to level 2 units are variable and whether level 2 profiles vary as a function of level 1 profiles. Results pointed to the presence of significant variability due to schools. (shrink)

Causal discovery becomes especially challenging when the possibility of latent confounding and/or selection bias is not assumed away. For this task, ancestral graph models are particularly useful in that they can represent the presence of latent confounding and selection effect, without explicitly invoking unobserved variables. Based on the machinery of ancestral graphs, there is a provably sound causal discovery algorithm, known as the FCI algorithm, that allows the possibility of latent confounders and selection bias. However, the (...) orientation rules used in the algorithm are not complete. In this paper, we provide additional orientation rules, augmented by which the FCI algorithm is shown to be complete, in the sense that it can, under standard assumptions, discover all aspects of the causal structure that are uniquely determined by facts of probabilistic dependence and independence. The result is useful for developing any causal discovery and reasoning system based on ancestral graph models. (shrink)

Acknowledging separable factors underlying negative symptoms may lead to better understanding and treatment of negative symptoms in individuals with schizophrenia. The current study aimed to test whether the negative symptoms factor (NSF) of the Positive and Negative Syndrome Scale (PANSS) would be better represented by expressive and experiential deficit factors, rather than by a single factor model, using confirmatory factor analysis (CFA). Two hundred and twenty individuals with schizophrenia spectrum disorders completed the PANSS; subsamples additionally completed the Brief Negative Symptom (...) Scale (BNSS) and the Motivation and Pleasure Scale—Self-Report (MAP-SR). CFA results indicated that the two-factor model fit the data better than the one-factor model; however, latent variables were closely correlated. The two-factor model’s fit was significantly improved by accounting for correlated residuals between N2 (emotional withdrawal) and N6 (lack of spontaneity and flow of conversation), and between N4 (passive social withdrawal) and G16 (active social avoidance), possibly reflecting common method variance. The two NSF factors exhibited differential patterns of correlation with subdomains of the BNSS and MAP-SR. These results suggest that the PANSS NSF would be better represented by a two-factor model than by a single-factor one, and support the two-factor model’s adequate criterion-related validity. Common method variance among several items may be a potential source of measurement error under a two-factor model of the PANSS NSF. (shrink)

We report a Monte Carlo study examining the effects of two strategies for handling measurement non-invariance – modeling and ignoring non-invariant items – on structural regression coefficients between latent variables measured with item response theory models for categorical indicators. These strategies were examined across four levels and three types of non-invariance – non-invariant loadings, non-invariant thresholds, and combined non-invariance on loadings and thresholds – in simple, partial, mediated and moderated regression models where the non-invariant latent (...) class='Hi'>variable occupied predictor, mediator, and criterion positions in the structural regression models. When non-invariance is ignored in the latent predictor, the focal group regression parameters are biased in the opposite direction to the difference in loadings and thresholds relative to the referent group (i.e., lower loadings and thresholds for the focal group lead to overestimated regression parameters). With criterion non-invariance, the focal group regression parameters are biased in the same direction as the difference in loadings and thresholds relative to the referent group. While unacceptable levels of parameter bias were confined to the focal group, bias occurred at considerably lower levels of ignored non-invariance than was previously recognized in referent and focal groups. (shrink)

ObjectivesUnder the COVID-19 prevention and control policy, online learning has been widely used. The current study aimed to identify latent profiles of self-regulated learning in the context of online mathematics learning during the recurrent outbreak of COVID-19, and examine the mechanisms underlying the relationship between self-regulated learning and online mathematics learning engagement among Chinese junior high school students using variable-and person-centered approaches.MethodsA sample of 428 Chinese junior high school students completed questionnaires on self-regulated learning, perceived academic control, and (...) learning engagement. Mplus7.0 was used to analyze the latent classes of self-regulated learning. A mediation model was conducted using the software SPSS PROCESS macro.ResultsThree profiles of self-regulated learning were identified and named as low self-regulated learning, medium self-regulated learning, and high self-regulated learning. In the mediating analysis, results of the variable-centered approach showed that perceived academic control mediated the effects of self-regulated learning on learning engagement. For the person-centered approach, we selected the low self-regulated learning type as the reference profile, and the analysis revealed that compared with the reference profile, perceived academic control partially mediated the link between the medium self-regulated learning profile and learning engagement; perceived academic control partially mediated the relationship between the high self-regulated learning profile and learning engagement.ConclusionThis study showed the heterogeneity in the online mathematics self-regulated learning patterns of Chinese junior high school students during the COVID-19 pandemic, revealing the internal mechanisms of Chinese junior high school students’ online mathematics learning engagement using variable-and person-centered approaches. Furthermore, the findings of the study have important implications for promoting online mathematics learning engagement among junior high students during the pandemic. (shrink)