Thought-action fusion: a comprehensive analysis using structural equation modeling

Thought-action fusion (TAF), the phenomenon whereby one has difficulty separating cognitions from corresponding behaviors, has implications in a wide variety of disturbances, including eating disorders, obsessive-compulsive disorder, generalized anxiety disorder, and panic disorder. Numerous constructs believed to contribute to the etiology or maintenance of TAF have been identified in the literature, but to date, no study has empirically integrated these findings into a comprehensive model. In this study, we examined simultaneously an array of variables thought to be related to TAF, and subsequently developed a model that elucidates the role of those variables that seem most involved in this phenomenon using a structural equation modeling approach. Results indicated that religiosity, as predicted by ethnic identity, was a significant predictor of TAF. Additionally, the relation between ethnic identity and TAF was partially mediated by an inflated sense of responsibility. Both TAF and obsessive-compulsive symptoms were found to be significant predictors of engagement in neutralization activities. Clinical and theoretical implications are discussed.     

A Macintosh and Windows program for assessing body-image disturbance using adjustable image distortion

Body image is one of the most important concepts in the study of eating disorders. The assessment and treatment of body-image issues are considered to be integral aspects of assessment and clinical management of eating disorders (Thompson, 1996b). The program, BodyImage, is software for the assessment of body-image disturbance. It uses an image-distorting technique to estimate body size. The image of the whole body or parts of the body can be captured as a digital image by a digital camera. Response data from participants are recorded as ASCII files so that other computer programs such as spreadsheets or word processing programs can handle the data. BodyImage works on personal computers, both Macintosh and Windows. It is available at no cost, and it can be obtained from the following URL: http://homepage2.nifty.com/s_shibata/softwares/bodyimage.html.     

Clarifying the role of impulsivity in dietary restraint: A structural equation modeling approach

This study was designed to clarify the relationship between the four dimensions of impulsivity in Whiteside and Lynam’s (2001) model and the two aspects of dietary restraint (Concern for Dieting and Weight Fluctuation) in a non-clinical sample. Data were collected from a volunteer community sample (N = 216) of women who responded to two self-report instruments related to impulsivity (UPPS Impulsive Behavior Scale, Whiteside & Lynam, 2001) and dietary restraint (Restraint Scale, Polivy, Herman, & Warsh, 1978). A structural equation model was tested. The model provided a good fit to the data (χ²/df = 1.64, p < .0001, RMSEA = 0.054, 90% CI = 0.050–0.058, p-value for test of close fit (RMSEA > 0.05) = .035) and revealed that Concern for Dieting was positively related to Urgency (standardized β = 0.25, p < .01). Weight Fluctuation was related to lack of Perseverance (standardized β = 0.25, p < .01) and tended to relate to Sensation Seeking (standardized β = 0.17, p = .056). Urgency and lack of Perseverance were found to play a significant role in predicting Concern for Dieting and Weight Fluctuation.     

Comparing standardized coefficients in structural equation modeling: a model reparameterization approach

We propose a two-stage method for comparing standardized coefficients in structural equation modeling (SEM). At stage 1, we transform the original model of interest into the standardized model by model reparameterization, so that the model parameters appearing in the standardized model are equivalent to the standardized parameters of the original model. At stage 2, we impose appropriate linear equality constraints on the standardized model and use a likelihood ratio test to make statistical inferences about the equality of standardized coefficients. Unlike other existing methods for comparing standardized coefficients, the proposed method does not require specific modeling features (e.g., specification of nonlinear constraints), which are available only in certain SEM software programs. Moreover, this method allows researchers to compare two or more standardized coefficients simultaneously in a standard and convenient way. Three real examples are given to illustrate the proposed method, using EQS, a popular SEM software program. Results show that the proposed method performs satisfactorily for testing the equality of standardized coefficients.     

Examining a multidimensional model of student motivation and engagement using a construct validation approach

Background. This study seeks to examine a multidimensional model of student motivation and engagement using within‐ and between‐network construct validation approaches. Aims. The study tests the first‐ and higher‐order factor structure of the motivation and engagement wheel and its corresponding measurement tool, the Motivation and Engagement Scale – High School (MES‐HS; formerly the Student Motivation and Engagement Scale). Sample. The study draws upon data from 12,237 high school students from 38 Australian high schools. Methods. The hypothesized 11‐factor first‐order structure and the four‐factor higher‐order structure, their relationship with a set of between‐network measures (class participation, enjoyment of school, educational aspirations), factor invariance across gender and year‐level, and the effects of age and gender are examined using confirmatory factor analysis and structural equation modelling. Results. In terms of within‐network validity, (1) the data confirm that the 11‐factor and higher‐order factor models of motivation and engagement are good fitting and (2) multigroup tests showed invariance across gender and year levels. In terms of between‐network validity, (3) correlations with enjoyment of school, class participation and educational aspirations are in the hypothesized directions, and (4) girls reflect a more adaptive pattern of motivation and engagement, and year‐level findings broadly confirm hypotheses that middle high school students seem to reflect a less adaptive pattern of motivation and engagement. Conclusion. The first‐ and higher‐order structures hold direct implications for educational practice and directions for future motivation and engagement research.     

Attitudinal body-image assessment: factor analysis of the Body-Self Relations Questionnaire

This article presents an analysis of the factor structure of the Body-Self Relations Questionnaire (BSRQ), an attitudinal body-image instrument. Random stratified samples, drawn from a national survey, included 1,064 females and 988 males. In order to evaluate the replicability of the BSRQ factor structure, separate split-sample factor analyses (principal components with varimax rotation) were conducted for each sex. Largely consistent with the conceptual basis of the BSRQ, the resultant factors derived from each analysis were: Appearance Evaluation, Appearance Orientation, Fitness Evaluation, Fitness Orientation, Health Evaluation, Health Orientation, and Illness Orientation. Subsequent concordance analyses revealed marked stability of the factor structure both within and between sexes. Females demonstrated somewhat greater differentiation of body-image attitudes than did males. The utility of the BSRQ is discussed relative to extant body-image measures.     

结构方程模型统计检验力分析：原理与方法

结构方程模型是心理学、管理学、社会学等学科中重要的统计工具之一。然而, 大量使用结构方程模型的研究忽视了对该方法的统计检验力进行必要的分析和报告, 在一定程度上降低了这些研究的结果的证明效力。结构方程模型的统计检验力分析方法主要有Satorra-Saris法、MacCallum法与Monte Carlo法三类。其中Satorra-Saris法适用于备择模型清晰、检验对象相对简单、检验方法基于χ²分布的情形; MacCallum法适用于基于χ²分布的模型拟合检验且备择模型不明的情形; Monte Carlo法适用于检验对象相对复杂、采用模拟或重抽样方法进行检验的情形。在实际应用中, 研究者应当首先判断检验的目的、方法以及是否有明确的备择模型, 并根据这些信息选择具体的分析方法。     

Meta-analytic structural equation modeling: a two-stage approach

To synthesize studies that use structural equation modeling (SEM), researchers usually use Pearson correlations (univariate r), Fisher z scores (univariate z), or generalized least squares (GLS) to combine the correlation matrices. The pooled correlation matrix is then analyzed by the use of SEM. Questionable inferences may occur for these ad hoc procedures. A 2-stage structural equation modeling (TSSEM) method is proposed to incorporate meta-analytic techniques and SEM into a unified framework. Simulation results reveal that the univariate-r, univariate-z, and TSSEM methods perform well in testing the homogeneity of correlation matrices and estimating the pooled correlation matrix. When fitting SEM, only TSSEM works well. The GLS method performed poorly in small to medium samples.     

Measuring change for a multidimensional test using a generalized explanatory longitudinal item response model

Even though many educational and psychological tests are known to be multidimensional, little research has been done to address how to measure individual differences in change within an item response theory framework. In this paper, we suggest a generalized explanatory longitudinal item response model to measure individual differences in change. New longitudinal models for multidimensional tests and existing models for unidimensional tests are presented within this framework and implemented with software developed for generalized linear models. In addition to the measurement of change, the longitudinal models we present can also be used to explain individual differences in change scores for person groups (e.g., learning disabled students versus non‐learning disabled students) and to model differences in item difficulties across item groups (e.g., number operation, measurement, and representation item groups in a mathematics test). An empirical example illustrates the use of the various models for measuring individual differences in change when there are person groups and multiple skill domains which lead to multidimensionality at a time point.     

A multidimensional item response model: Constrained latent class analysis using the gibbs sampler and posterior predictive checks

In this paper it will be shown that a certain class of constrained latent class models may be interpreted as a special case of nonparametric multidimensional item response models. The parameters of this latent class model will be estimated using an application of the Gibbs sampler. It will be illustrated that the Gibbs sampler is an excellent tool if inequality constraints have to be taken into consideration when making inferences. Model fit will be investigated using posterior predictive checks. Checks for manifest monotonicity, the agreement between the observed and expected conditional association structure, marginal local homogeneity, and the number of latent classes will be presented.This paper is supported by grant S40-645 of the Dutch Organization for Scientific Research (NWO).     

Schema induction in problem solving: a multidimensional analysis

The present research examined the processes of schema formation in problem solving. In 4 experiments, participants experienced a series of tasks analogous to A. S. Luchins' (1942) water jar problems before attempting to solve isomorphic target problems. Juxtaposing illustrative source instances varying in procedural features along multiple dimensions promoted the construction of a general schema that facilitated solving an isomorphic problem requiring a novel procedure. Exposure to less variant problems led to faster initial learning, but narrower and fixed schemas (mental set), whereas exposure to variant procedures led to slower initial learning, but broader and more flexible schemas. The findings support the dimensional specificity hypothesis: Generalization along 1 dimension facilitates transfer to a target problem differing from the source problems in that dimension.     

Clarifying boundary issues in psychopathology: the role of taxometrics in a comprehensive program of structural research

Despite decades of debate, important questions about the boundaries that separate psychological disorder from normality and that distinguish 1 disorder from another remain largely unanswered. These issues pose empirical questions that may be addressed by assessing the latent structure of psychopathological constructs. Because these constructs are likely to be structurally complex, and no single statistical tool addresses all structural questions, it is proposed in this article that boundary issues be examined through programmatic research grounded in the taxometric method and elaborated by complementary analyses. The authors describe how such a program could delimit the structure of disorders and test competing explanations of diagnostic co-occurrence, emphasizing the potential to enhance the reliability and validity of assessment, maximize the power of research designs, and improve diagnostic classification.     

The problem of model selection uncertainty in structural equation modeling

Model selection in structural equation modeling (SEM) involves using selection criteria to declare one model superior and treating it as a best working hypothesis until a better model is proposed. A limitation of this approach is that sampling variability in selection criteria usually is not considered, leading to assertions of model superiority that may not withstand replication. We illustrate that selection decisions using information criteria can be highly unstable over repeated sampling and that this uncertainty does not necessarily decrease with increases in sample size. Methods for addressing model selection uncertainty in SEM are evaluated, and implications for practice are discussed.     

Antecedents and consequences of workplace bullying: a longitudinal analysis with a structural equation model

Most studies focusing on the antecedents and consequences of workplace bullying have used a cross-sectional design, which impedes determining the causality of the relationships. In the present work, we analyzed, by means of structural equation models, the relationship between workplace bullying and some variables that are considered antecedents (interpersonal conflicts, role ambiguity, role conflict, and workplace social support) or consequences (health complaints and inclination to absenteeism from work) of this phenomenon. Multicenter study with two phases. The sample consisted of 696 employees from 66 centers. Workplace bullying was assessed by means of the "Mobbing-UNIPSICO" questionnaire, and the other variables with frequency scales. The cross-sectional models indicated a significant association between role conflict, workplace social support, and workplace bullying in both study periods. Concerning the longitudinal relationships, only workplace social support was a significant predictor of workplace bullying, which, in turn, was a cross-sectional and longitudinal predictor of workers' health complaints. Our results show the mediating effect of workplace bullying between certain work conditions and health complaints, and it is recommendable to replicate these findings in a multi-occupational sample.     

Group cohesion: A new multidimensional model

Based upon a careful perusal of all major theoretical reviews and most available controlled, empirical studies from the last 30 years, a five factor model of group cohesion is proposed. These factors are: attraction and bonding; support and caring; listening and empathy; self-disclosure and feedback; and process performance and goal attainment. To understand more fully the complex phenomenon of group cohesion, certain preconditions to the cohesive therapy group must be considered. The most significant of these are: selection of suitable participants; a balanced composition of the group; and effective orientation, training, and contracting. Important early group conditions are: resolving conflict and rebellion; constructive norming and culture building; and reducing avoidance and defensiveness. This new, generic, multidimensional model of group cohesion should prove of great value both to the clinician and the researcher in the group psychotherapy field and related areas.The author is indebted to the following colleagues for constructive criticisms of earlier versions of this report: S. Budman, R. R. Dies, K. R. MacKenzie, W. E. Piper, M. A. Richardsen, and I. D. Yalom.     

The relationship between personality, social functioning, and depression: a structural equation modeling analysis

The relationship between personality, social functioning, and depression remains unclear. The present study employs structural equation modeling to examine the mediating role of social functioning between harm avoidance (HA), self-directedness (SD), and depression. A sample of 902 individuals completed a self-report questionnaire consisting of the following scales: HA and SD subscales of the Temperament and Character Inventory (TCI), Beck Depression Inventory (BDI), and Social Adaptation Self-Evaluation Scale (SASS). Structural equation modeling via analysis of moment structure was used to estimate the fit of nine related models. Results indicated that social functioning is a mediator between harm avoidance or self-directness and depression. Self-directedness was also shown to have direct effects on depression. The results support the social reinforcement theory of depression and provide a theoretical account of how the variables are related based on correlation methods. Suggestions are offered for future experimental and longitudinal research.     

The structure of personality disorders: comparing the DSM-IV-TR Axis II classification with the five-factor model framework using structural equation modeling

Earlier factor analytical studies on the empirical validity of the DSM-IV-TR (American Psychological Association, 2000) Axis II classification have offered little support for the current three-cluster structure. In his large-scale meta-analysis of previously published personality disorder correlation matrices, O'Connor (2005) found four factors, corresponding to the neuroticism, extraversion, agreeableness, and conscientiousness domains of the five-factor model of personality. In the present study, this dimensional four-factor model and the categorical DSM three-cluster structure were fitted to the Assessment of DSM-IV Personality Disorders questionnaire (ADP-IV; Schotte & De Doncker, 1994) scale scores using structural equation modelling. The results strongly favored the dimensional model, which also resembled other well-founded four-factor proposals (Livesley, Jang, & Vernon, 1998; Widiger & Simonsen, 2005). Moreover, a multigroup confirmatory factor analysis showed that this model was highly invariant and thus generalizable across two large clinical (n = 1,029) and general population (n = 659) samples.     

An individual difference model for the multidimensional analysis of preference data

A model for the analysis of paired comparison data is presented which combines features of the BTL-model with features of the Unfolding model. The model is metric, mathematically tractable, and has an exact algebraic solution. Since it is multidimensional and allows for individual differences, it is thought to be more realistic for some choice situations than either the Thurstone model or the BTL-model. No claim is made that the present model will be appropriate for all conceivable choice situations. Rather, it is argued that the fact that it is explicitly falsifiable is a point in its favor.This work was supported by a grant of the United States Public Health Service (1 R03 MH19139 01 MSM) and a David Ross (XR) grant of the Purdue Research Foundation (PRF 2132), both of which are gratefully acknowledged. We also owe thanks to Dr. Terry Cooper, whose careful scrutiny of an earlier draft of this paper allowed us to reduce the number of errors from n to n-1.     

A marginalization model for the multidimensional unfolding analysis of ranking data

A marginalization model for the multidimensional unfolding analysis of ranking data is presented. A subject samples one of a number of random points that are multivariate normally distributed. The subject perceives the distances from the point to all the stimulus points fixed in the same multidimensional space. The distances are error perturbed in this perception process. He/she produces a ranking dependent on these error-perturbed distances. The marginal probability of a ranking is obtained according to this ranking model and by integrating out the subject (ideal point) parameters, assuming the above distribution. One advantage of the model is that the individual differences are captured using the posterior probabilities of subject points. Three sets of ranking data are analyzed by the model.