Phillip David Parker

Exploratory Structural Equation Modeling: An Integration of the Best Features of Exploratory and Confirmatory Factor Analysis

Exploratory factor analysis (EFA) and confirmatory factor analysis (CFA), path analysis, and structural equation modeling (SEM) have long histories in clinical research. Although CFA has largely superseded EFA, CFAs of multidimensional constructs typically fail to meet standards of good measurement: goodness of fit, measurement invariance, lack of differential item functioning, and well-differentiated factors in support of discriminant validity. Part of the problem is undue reliance on overly restrictive CFAs in which each item loads on only one factor. Exploratory SEM (ESEM), an overarching integration of the best aspects of CFA/SEM and traditional EFA, provides confirmatory tests of a priori factor structures, relations between latent factors and multigroup/multioccasion tests of full (mean structure) measurement invariance. It incorporates all combinations of CFA factors, ESEM factors, covariates, grouping/multiple-indicator multiple-cause (MIMIC) variables, latent growth, and complex structures that typically have required CFA/SEM. ESEM has broad applicability to clinical studies that are not appropriately addressed either by traditional EFA or CFA/SEM.

Is Self-Esteem a Cause or Consequence of Social Support? A 4-Year Longitudinal Study

Considerable research has been devoted to examining the relations between self-esteem and social support. However, the exact nature and direction of these relations are not well understood. Measures of self-esteem, and social support quantity and quality were administered to 961 adolescents across five yearly time points (M(age) = 13.41 years). Structural equation modeling (SEM) was utilized to test between a self-esteem antecedent model (self-esteem precedes changes in social support), self-esteem consequence model (social support precedes change in self-esteem), and a reciprocal influence model. Self-esteem reliably predicted increasing levels of social support quality and network size across time. In contrast, the consequence model was not supported. The implications of this for helping adolescents to develop higher quality social support structures are discussed.

Nonattachment and mindfulness: Related but distinct constructs

In this study, we examined whether nonattachment, a relatively new construct in the mindfulness literature, showed convergent, discriminant, and incremental validity in relation to the well-studied 5 facets of mindfulness. Mindfulness was defined as a multifaceted construct including observing, describing, acting with awareness, nonjudging, and nonreactivity; and measured using the recently validated, 20-item Five Facet Mindfulness Questionnaire (FFMQ; Tran, Glück, & Nader, 2013; Baer, Smith, Hopkins, Krietemeyer, & Toney, 2006). Nonattachment was defined as a flexible, balanced way of relating to ones experiences without clinging to or suppressing them, and measured using the 7-item Nonattachment Scale (NAS-7; Elphinstone, Sahdra, & Ciarrochi, 2015; Sahdra, Shaver, & Brown, 2015). In a large nationally representative sample of Americans (N = 7,884; 52% women; age, M = 47.9, SD = 16), nonattachment was positively related to all 5 aspects of mindfulness. Structural equation modeling showed that the 20-item FFMQ and NAS-7 showed good fit; their factor structures were invariant across genders and age groups; and NAS-7 was empirically distinguishable from the 5 mindfulness facets. Hierarchical regression models provided evidence of the incremental validity of NAS-7. Finally, mediation models showed that nonattachment substantially mediated the links between the mindfulness facets and the outcome variables of satisfaction with life and life effectiveness. (PsycINFO Database Record

Physical Activity and School Engagement in Youth: A Systematic Review and Meta-Analysis.

Physical activity is associated with numerous health benefits in youth; however, these benefits could extend further than health, into education. Our aim was to systematically review and combine in meta-analyses evidence concerning the association between physical activity and the dimensions of school engagement, including behavior (e.g., time-on-task), emotions (e.g., lesson enjoyment), and cognition (e.g., self-regulated learning). We conducted meta-analyses using structural equation modeling on results from 38 studies. Overall, physical activity had a small, positive association with school engagement (d = .28, I2 = .86), 95% confidence interval [.12, .46]. This association was moderated by study design, with significant associations shown in randomized controlled trials but not in studies employing other designs. Risk of bias was also a significant effect moderator, as studies with a low risk of bias showed significant associations but not high risk of bias studies. Altogether, these results suggest that physical activity could improve school engagement.

The Development of Compulsive Internet Use and Mental Health: A Four-Year Study of Adolescence.

Is compulsive Internet use (CIU) an antecedent to poor mental health, a consequence, or both? Study 1 used a longitudinal design to track the development of CIU and mental health in Grade 8 (N = 1030 males, 1038 females, Mage = 13.7), 9, 10, and 11. Study 2 extended Study 1 by examining the kinds of Internet behaviors most strongly associated with CIU within males and females. Structural equation modeling revealed that CIU predicted the development of poor mental health, whereas poor mental health did not predict CIU development. Latent growth analyses showed that both females and males increased in CIU and mental health problems across the high school years. Females had higher CIU and worse mental health than males, and tended to engage in more social forms of Internet use. We discuss future directions for CIU intervention research.

Longitudinal associations between employees’ beliefs about the quality of the change management process, affective commitment to change and psychological empowerment

Organizational changes are costly ventures that too often fail to deliver the expected outcomes. Psychological empowerment and affective commitment to change are proposed as especially important in turbulent contexts characterized by multiple and ongoing changes requiring employees’ continuing contributions. In such a context, employees’ beliefs that the changes are necessary, legitimate and will be supported, are presumed to increase psychological empowerment and affective commitment to change. In a three-wave longitudinal panel study of 819 employees, we examined autoregressive and cross-lagged relations among latent constructs reflecting change-related beliefs (necessity, legitimacy, support) and psychological reactions (psychological empowerment, affective commitment to change). Our findings suggest that psychological empowerment and affective commitment to change represent largely orthogonal reactions, that psychological empowerment is influenced more by beliefs regarding support, whereas affective commitment to change is shaped more by beliefs concerning necessity and legitimacy.

A Multination Study of Socioeconomic Inequality in Expectations for Progression to Higher Education The Role of Between-School Tracking and Ability Stratification

Persistent inequalities in educational expectations across societies are a growing concern. Recent research has explored the extent to which inequalities in education are due to primary effects (i.e., achievement differentials) versus secondary effects (i.e., choice behaviors net of achievement). We explore educational expectations in order to consider whether variations in primary and secondary effects are associated with country variation in curricular and ability stratification. We use evidence from the PISA 2003 database to test the hypothesis that (a) greater between-school academic stratification would be associated with stronger relationships between socioeconomic status and educational expectations and (b) when this effect is decomposed, achievement differentials would explain a greater proportion of this relationship in countries with greater stratification. Results supported these hypotheses.

Internal/external frame of reference model

Self-concept is an important outcome variable that facilitates attainment of other desirable outcomes. Self-concept formation is based in part on the frames of reference or standards of comparison used to evaluate ones accomplishments. The internal/external frame of reference model posits dimensional comparisons such that accomplishments in one domain are used as a basis of comparison for evaluating accomplishments in other domains, along with the accomplishments of other individuals (social comparison). Based on extensive support in educational settings that generalizes across gender, age, and nationality, it explains why high achievement in one domain (e.g., mathematics) can have negative effects on self-concepts in another domain (verbal).

Using Genetic Algorithms in a Large Nationally Representative American Sample to Abbreviate the Multidimensional Experiential Avoidance Questionnaire

Genetic algorithms (GAs) are robust machine learning approaches for abbreviating a large set of variables into a shorter subset that maximally captures the variance in the original data. We employed a GA-based method to shorten the 62-item Multidimensional Experiential Avoidance Questionnaire (MEAQ) by half without much loss of information. Experiential avoidance or the tendency to avoid negative internal experiences is a key target of many psychological interventions and its measurement is an important issue in psychology. The 62-item MEAQ has been shown to have good psychometric properties, but its length may limit its use in most practical settings. The recently validated 15-item brief version (BEAQ) is one short alternative, but it reduces the multidimensional scale to a single dimension. We sought to shorten the 62-item MEAQ by half while maintaining fidelity to its six dimensions. In a large nationally representative sample of Americans (N = 7884; 52% female; Age: M = 47.9, SD = 16), we employed a GA method of scale abbreviation implemented in the R package, GAabbreviate. The GA-derived short form, MEAQ-30 with five items per subscale, performed virtually identically to the original 62-item MEAQ in terms of inter-subscales correlations, factor structure, factor correlations, and zero-order correlations and unique latent associations of the six subscales with other measures of mental distress, wellbeing and personal strivings. The two measures also showed similar distributions of means across American census regions. The MEAQ-30 provides a multidimensional assessment of experiential avoidance whilst minimizing participant burden. The study adds to the emerging literature on the utility of machine learning methods in psychometrics.