Regression Mixture Models: Does Modeling the Covariance Between Independent Variables and Latent Classes Improve the Results?

Regression mixture models are increasingly used as an exploratory approach to identify heterogeneity in the effects of a predictor on an outcome. In this simulation study, we tested the effects of violating an implicit assumption often made in these models; that is, independent variables in the model are not directly related to latent classes. Results indicate that the major risk of failing to model the relationship between predictor and latent class was an increase in the probability of selecting additional latent classes and biased class proportions. In addition, we tested whether regression mixture models can detect a piecewise relationship between a predictor and outcome. Results suggest that these models are able to detect piecewise relations but only when the relationship between the latent class and the predictor is included in model estimation. We illustrate the implications of making this assumption through a reanalysis of applied data examining heterogeneity in the effects of family resources on academic achievement. We compare previous results (which assumed no relation between independent variables and latent class) to the model where this assumption is lifted. Implications and analytic suggestions for conducting regression mixture based on these findings are noted.     

A Simple Simulation Technique for Nonnormal Data with Prespecified Skewness,Kurtosis, and Covariance Matrix

We present and investigate a simple way to generate nonnormal data using linear combinations of independent generator (IG) variables. The simulated data have prespecified univariate skewness and kurtosis and a given covariance matrix. In contrast to the widely used Vale-Maurelli (VM) transform, the obtained data are shown to have a non-Gaussian copula. We analytically obtain asymptotic robustness conditions for the IG distribution. We show empirically that popular test statistics in covariance analysis tend to reject true models more often under the IG transform than under the VM transform. This implies that overly optimistic evaluations of estimators and fit statistics in covariance structure analysis may be tempered by including the IG transform for nonnormal data generation. We provide an implementation of the IG transform in the R environment.     

Dealing with Multiple Solutions in Structural Vector Autoregressive Models

Structural vector autoregressive models (VARs) hold great potential for psychological science, particularly for time series data analysis. They capture the magnitude, direction of influence, and temporal (lagged and contemporaneous) nature of relations among variables. Unified structural equation modeling (uSEM) is an optimal structural VAR instantiation, according to large-scale simulation studies, and it is implemented within an SEM framework. However, little is known about the uniqueness of uSEM results. Thus, the goal of this study was to investigate whether multiple solutions result from uSEM analysis and, if so, to demonstrate ways to select an optimal solution. This was accomplished with two simulated data sets, an empirical data set concerning children's dyadic play, and modifications to the group iterative multiple model estimation (GIMME) program, which implements uSEMs with group- and individual-level relations in a data-driven manner. Results revealed multiple solutions when there were large contemporaneous relations among variables. Results also verified several ways to select the correct solution when the complete solution set was generated, such as the use of cross-validation, maximum standardized residuals, and information criteria. This work has immediate and direct implications for the analysis of time series data and for the inferences drawn from those data concerning human behavior.     

Time-Varying Treatments in Observational Studies: Marginal Structural Models of the Effects of Early Grade Retention on Math Achievement

One of the main objectives of many empirical studies in the social and behavioral sciences is to assess the causal effect of a treatment or intervention on the occurrence of a certain event. The randomized controlled trial is generally considered the gold standard to evaluate such causal effects. However, for ethical or practical reasons, social scientists are often bound to the use of nonexperimental, observational designs. When the treatment and control group are different with regard to variables that are related to the outcome, this may induce the problem of confounding. A variety of statistical techniques, such as regression, matching, and subclassification, is now available and routinely used to adjust for confounding due to measured variables. However, these techniques are not appropriate for dealing with time-varying confounding, which arises in situations where the treatment or intervention can be received at multiple timepoints. In this article, we explain the use of marginal structural models and inverse probability weighting to control for time-varying confounding in observational studies. We illustrate the approach with an empirical example of grade retention effects on mathematics development throughout primary school.     

A Note on Recurring Misconceptions When Fitting Nonlinear Mixed Models

Nonlinear mixed-effects (NLME) models are used when analyzing continuous repeated measures data taken on each of a number of individuals where the focus is on characteristics of complex, nonlinear individual change. Challenges with fitting NLME models and interpreting analytic results have been well documented in the statistical literature. However, parameter estimates as well as fitted functions from NLME analyses in recent articles have been misinterpreted, suggesting the need for clarification of these issues before these misconceptions become fact. These misconceptions arise from the choice of popular estimation algorithms, namely, the first-order linearization method (FO) and Gaussian-Hermite quadrature (GHQ) methods, and how these choices necessarily lead to population-average (PA) or subject-specific (SS) interpretations of model parameters, respectively. These estimation approaches also affect the fitted function for the typical individual, the lack-of-fit of individuals’ predicted trajectories, and vice versa.     

The role of repetitive thought in determining posttraumatic growth and distress following interpersonal trauma

Background and Objectives: Repetitive thought (RT) strategies have been linked to a range of negative outcomes following traumatic interpersonal events but are proposed to serve an adaptive function under particular circumstances. This study examined outcomes following RT within a transdiagnostic framework, and explored the potentially adaptive nature of trait-like and event-related RT. Design: The centrality of a traumatic event to one's identity was explored as a context under which the adaptive nature of RT might change. Young adults with interpersonal violence experiences (N = 163) reported use of trait-like and event-related RT, centrality of the event, depressive, anxious, and posttraumatic stress symptoms (PTSS), posttraumatic depreciation and posttraumatic growth. Methods: Hierarchical multiple regression analyses were used to examine main and moderating effects of four types of RT and event centrality on outcome variables. Results: Centrality positively predicted depressive symptoms and PTSS, depreciation, and growth. Brooding RT positively predicted all negative outcomes. Reflecting RT positively predicted anxious symptoms and PTSS and depreciation. Only deliberate RT positively predicted growth. Centrality did not moderate any examined relationships. Conclusions: Findings highlight the importance of addressing specific types of RT in interventions with survivors and of considering centrality as a robust contributor to outcomes following interpersonal violence.     

Acute stress disorder among civilians during a war and post-traumatic growth six years later: the impact of personal and social resources

Background and Objectives: Various studies suggest a link between stress response to a traumatic event and post-traumatic growth (PTG), but little is known about their long-term relationship. In this study, the relationship between acute stress disorder (ASD) among civilians during a war on the home front and PTG six years later was examined for the first time. Based on the conservation of resources (COR) theory, the role of personal and social resource loss and gain as moderating factors was investigated. Design and Methods: At Time 1 of the research (the Second Lebanon War in 2006), a structured questionnaire was administered to 370 civilians living within rocket range. At Time 2, 6 years later, 301 participants from Time 1 were again examined. The data analysis refers to the 301 respondents who participated at Time 2. Results: The findings indicate a significant relationship between ASD and PTG. Examination of the interaction revealed that resource gain (but not resource loss) moderates (strengthens) the relationship between the two. Conclusions: These findings are not consistent with the COR view that resource loss has a greater effect on stress responses than resource gain.     

Temporal dynamics of need satisfaction and need frustration. Two sides of the same coin?

We study the dynamics of need satisfaction and need frustration by examining how need satisfaction and need frustration change over time and how these changes relate to changes in motivation. To investigate this, volunteers were assessed daily during a delineated activity, resulting in a total sample of 77 volunteers and 467 completed daily diaries. Bayesian confirmatory factor analysis on the within-person level confirmed a bifactor solution: autonomy, competence, and relatedness were distinguished by three specific factors, but the majority of variance was explained by two strongly correlated (need satisfaction and need frustration) factors. The strong correlation between need satisfaction and need frustration further translated in the development of their relationship over time. That is, Bayesian latent growth curve modelling revealed a simultaneous, yet opposite, growth curve. Contrary to our expectations, neither of them could be related to behavioural internalization or externalization. These results imply that, at the within-person level, momentary need satisfaction and frustration are difficult to distinguish, and affecting one may automatically affect the other. Also, the relationships within the self-determination framework, such as the proposed link between need satisfaction and behavioural internalization may be better reframed with attention to the time-frame in which they occur.     

Vicarious trauma: The psychological impact of working with survivors of trauma for South African psychologists

Traumatic events are highly prevalent in South African society and psychologists who work with survivors of trauma have been identified as particularly at risk of being adversely affected by their work, and experiencing vicarious trauma. This study aimed to explore the experiences of a group of South African psychologists who work predominantly with trauma survivors. Individual semi-structured interviews were conducted with six psychologists (females = 67%). The predominant type of trauma encountered by participants in clinical practice was interpersonal trauma in the form of physical and sexual abuse (83%). Data were analysed using thematic analysis. All participants reported symptoms of vicarious trauma including disruption in cognitive schemas, symptoms characteristic of post-traumatic stress disorder, and somatic symptoms. Participants also reported vicarious post-traumatic growth including an enhanced sense of interpersonal connectedness and positive changes in their philosophy of life and self-perceptions. The findings serve to sensitise psychologists to the impact of working with trauma survivors so as to enhance the efficiency of psychological service delivery to traumatised populations.     

Expertise in soccer teams: A thematic inquiry into the role of Shared Mental Models within team chemistry

AimsThe purpose of the current study was to establish a conceptual framework of team chemistry components in sport with an emphasis on Shared Mental Models (SMM).MethodElite soccer coaches (n = 6) and players (n = 3) were interviewed using a semi-structured interview guide. An inductive thematic analysis was employed to analyze the data.ResultsFour themes related to team chemistry components were identified: (1) members' characteristics (i.e., demographic data, on-field characteristics, and member's ego), (2) coach–players interactions (i.e., professional interaction and emotional intelligence of coaches), (3) interactions among the players (i.e., professional understanding, efficacy beliefs, team cohesion, players' emotional intelligence, team roles, and goals), and (4) interactions with environmental factors (i.e., owners, management, fans, and media).ConclusionsThe cognitive components of the team chemistry model were clustered to establish a conceptual framework of SMM. Furthermore, the cognitive-affective-social-behavioral linkage of team chemistry and athletic performance is examined in light of the emerged model and conceptual framework. Implications and future directions are also discussed.