Estimating, testing, and comparing specific effects in structural equation models: The phantom model approach.

The phantom model approach for estimating, testing, and comparing specific effects within structural equation models (SEMs) is presented. The rationale underlying this novel method consists in representing the specific effect to be assessed as a total effect within a separate latent variable model, the phantom model that is added to the main model. The following favorable features characterize the method: (a) It enables the estimation, testing, and comparison of arbitrary specific effects for recursive and nonrecursive models with latent and manifest variables; (b) it enables the bootstrapping of confidence intervals; and (c) it can be applied with all standard SEM programs permitting latent variables, the specification of equality constraints, and the bootstrapping of total effects. These features along with the fact that no manipulation of matrices and formulas is required make the approach particularly suitable for applied researchers. The method is illustrated by means of 3 examples with real data sets. (PsycINFO Database Record (c) 2011 APA, all rights reserved)     

Drug use and unprotected anal intercourse among gay men.

Examined the link between unprotected insertive and receptive anal intercourse and drug use with sex in 604 gay men. Data spanning 4 12-mo periods from 1980 to 1987 indicate that the link between drug use and high-risk sex diminished as the acquired immune deficiency syndrome (AIDS) epidemic progressed. Strong and significant cross-sectional associations were found between drug use with sex and both types of anal intercourse in the year prior to the onset of AIDS. By 1987 the magnitude of these associations was markedly reduced. Findings support both causal and noncausal interpretations of the link between substance use and high-risk sex among gay men. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Associations of substance use problems with intimate partner violence for at-risk men in long-term relationships.

Associations of substance use problems in men--defined as a man's meeting at least 1 criterion of dependence on each of a number of substances by his mid-20s--with their perpetration of intimate partner violence (IPV) were examined in an at-risk community sample of 150 men in long-term relationships from their late adolescence to their late 20s. Men who had a problem with substances other than sedatives (especially cannabis and hallucinogens) committed more IPV than did men without such problems. Most of the men who had a problem with marijuana also had an alcohol problem, which explains why alcohol was found to have only an indirect association with IPV. The failure of previous alcohol-use studies to control for co-occurrence of alcohol and marijuana problems may explain the discrepancy with conclusions from past research that alcohol problems contribute directly to the perpetration of IPV. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

An introduction to using structural equation models in rehabilitation psychology.

Objective: To provide an overview of structural equation modeling (SEM) using an example drawn from the rehabilitation psychology literature. Design: To illustrate the 5 steps in SEM (model specification, identification, estimation methods, interpretation of results, and model modification), an example is presented, with details on determining whether alternative models result in a significant improvement to fit to the observed data. Data are from a sample of 274 people with spinal cord injury. Issues commonly encountered in preparing data for SEM analyses (e.g., missing data, nonnormality) are reviewed, as is the debate surrounding some aspects of SEM (e.g., acceptable sample size). Conclusion: SEM can be a powerful procedure for empirically representing complex and sophisticated theoretical models of interest to rehabilitation psychologists. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Parent drug-use problems and adult intimate relations: Associations among community samples of young adult women and men.

Clinical and anecdotal evidence suggests that being raised by drug-abusing parents may create problems with intimacy in later life. Nearly all previous work has failed to consider other types of family dysfunction as a precursor to problems with adult intimacy. Many empirical analyses of adult children of drug users (ACDUs) have been compromised by several methodological and conceptual inadequacies, including sample biases, overly simplistic operationalization of ACDU status, and limited analytic procedures. Structural equation models were used to analyze data from a community sample of men and women to address many of these defects. For both women and men, parent drug-use problems predicted poor family support, and family support was strongly associated with good adult intimate relations. Furthermore, for men, more parent drug-use problems reduced dyadic adjustment, increased dependence, and had a specific effect on reducing dating competence. For women, parent drug-use problems had no direct effects on adult intimacy or relationship variables. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Longitudinal risk factors for intimate partner violence among men in treatment for alcohol use disorders.

Objective: This study examined static and time-varying risk factors for perpetration of intimate partner violence (IPV) among men in treatment for alcohol use disorders. Method: Participants were 178 men diagnosed with alcohol abuse or dependence and their partners. Most (85%) of the men were European American; their average age was 41.0 years. Participants completed measures assessing initial alcohol problem severity, baseline beliefs related to alcohol use, antisocial personality characteristics, alcohol and drug use, relationship adjustment, and IPV. Results: According to couples' reconciled reports, 42% of participants perpetrated IPV at baseline. Among this group, the IPV recurrence rate was 43% at 6-month follow-up and 36% at 12-month follow-up. For participants without IPV perpetration at baseline, new incidence of IPV was 15% and 7% at the 6-month and 12-month follow-up points, respectively. Fixed marker predictors of IPV rates included baseline alcohol problem severity variables, baseline beliefs related to alcohol use, and antisocial personality characteristics. Variable risk factor predictors included alcohol and drug use variables, relationship adjustment factors, and anger. Alcohol use variables and anger were associated with new incidents of IPV among those without reported IPV at baseline only. Conclusions: Findings suggest that assessing and monitoring IPV occurrence by both partners is important for men in treatment for alcohol use disorders. Results indicate vulnerability factors that may identify individuals at risk for IPV and provide targets for IPV prevention among those with alcohol use disorders. These findings can aid in the development of more comprehensive models that more precisely predict IPV. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Workplace anger and aggression: Informing conceptual models with data from specific encounters.

Workplace aggression is typically assessed by reports of the frequency of aggressive behaviors aggregated across incidents. Relations tested using such assessments are limited in the information they can provide about the operation of aggression within the context of a specific encounter. Analysis of data from structured interviews and questionnaire reports of employee experiences of specific workplace aggression incidents (as the target and as the aggressor) examine a variety of perceived antecedents, aggressive behaviors, and outcomes. Results suggest a variety of organizational, job-related, and personal antecedents, such as job stress and conflicts, and job-related outcomes, such as dissatisfaction. These data provide insight into the patterning of aggressive behaviors within an encounter and suggest an escalatory pattern. Data suggest relations between the severity of an aggressive encounter and the negativity of employee outcomes. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Analyzing data from experimental studies: A latent variable structural equation modeling approach.

This article illustrates the use of structural equation modeling (SEM) procedures with latent variables to analyze data from experimental studies. These procedures allow the researcher to remove the biasing effects of random and correlated measurement error on the outcomes of the experiment and to examine processes that may account for changes in the outcome variables that are observed. Analyses of data from a Project Family study, an experimental intervention project with rural families that strives to improve parenting skills, are presented to illustrate the use of these modeling procedures. Issues that arise in applying SEM procedures, such as sample size and distributional characteristics of the measures, are discussed. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

The role of drug use in a conceptual model of intimate partner violence in men and women arrested for domestic violence.

In a previous study, alcohol problems in perpetrators and their partners contributed directly and indirectly to intimate partner violence (IPV), even after including other correlates of violence in the model (G. L. Stuart et al., 2006). The present study extends these findings by examining the role of illicit drug use. We recruited 271 men and 135 women arrested for IPV and used structural equation modeling to examine the data. Results showed that drug use, as reported by the perpetrators, was a stronger predictor of IPV than were alcohol problems in perpetrators and their partners. Arrested males' marijuana use and stimulant use (i.e., cocaine and amphetamines) were associated with perpetration of IPV, and their report of their female partners' stimulant use was associated with her violence perpetration. In arrested women, specific substances used did not predict violence perpetration beyond other model variables; however, female perpetrators' report of male partners' stimulant use predicted male psychological and physical aggression, after controlling for other variables. These results provide further evidence that drug problems by both partners may be important in the evolution of aggression. Implications for batterer intervention programs are discussed. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

A prospective study of the association between obesity and burnout among apparently healthy men and women.

The authors prospectively tested the hypothesis that obesity predicts burnout and the reverse-causation hypothesis that burnout predicts obesity. Respondents were 724 men and 340 women, apparently healthy employees, who underwent routine periodic health examinations at 2 points of time about 18 months apart. Obesity was assessed by body mass index, waist-hip ratio, and waist circumference. In regression analyses, done separately for men and women, the authors controlled for depressive symptomatology, sport activity, and Time 1 levels of the criterion. The hypothesis that burnout predicts obesity was not supported. The authors found that Time 1 measures of obesity predicted reductions rather than the hypothesized elevations of Time 2 burnout levels. The authors also found that for male respondents with relatively higher levels of Time 1 burnout, the higher their level of Time 1 obesity measure, the lower their level of T2 burnout. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Analysis of interaction terms in structural equation models: A non-technical demonstration using the deviation score approach.

One of the major shortcomings in using structural equation modeling (SEM) data analytic techniques has been the difficulty in handling interaction terms in the modeling process. The issue is that interaction terms that are created by cross-multiplying raw scores result in the matrix of covariances or correlations being singular (there is at least 1 linear dependency in the matrix). The data analyses will not proceed as the matrix is not positive definite. This paper shows a valid and easy way to cope with the problem of interaction terms by using deviation scores or centred variables as the interaction terms. The authors expand on the work of L. S. Aiken and S. G. West (1991), which discussed interaction effects within a multiple regression framework, by taking it into the SEM domain for the benefit of users of SEM programs. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Causal effects of academic self-concept on academic achievement: Structural equation models of longitudinal data.

Academic self-concept, school marks, and teacher ratings of achievement were collected in 3 high-school subjects in each of 3 years (N?=?603). In the structural equation models (SEMs) considered, both school-based performance and academic self-concept were measured with multiple indicators for each school subject. SEMs were used to evaluate the effects of prior academic self-concept on subsequent achievement after controlling for the effects of prior achievement, and the effects of prior achievement on subsequent academic self-concept after controlling for the effects of prior academic self-concept. Although the effects of achievement tended to be larger and more systematic, there was clear support for both academic self-concept and achievement effects. Although there was support for this reciprocal effects model for all 3 school subjects, self-concept effects tended to be larger and more systematic for mathematics than for science and, particularly, English. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Additional adverse events among women exposed to intimate partner violence: Frequency and impact.

Objective: To assess additional adverse life events that women exposed to intimate partner violence (IPV) may have endured and to ascertain whether, and in what ways, problems in adjustment are related more to IPV or to IPV plus other adverse life events. Method: Predictors of the effects of exposure to adversities were investigated in this study of 104 women exposed to severe IPV who reported conflict tactics, adverse life events, as well as symptoms of distress. Results: The majority of participants experienced additional adversities (86%). Significant differences were found between those exposed to IPV-only and those exposed to IPV plus other adverse events in terms of IPV frequency and current symptoms of distress. Women with IPV plus other adverse events had twice as many physical assaults and 4 times as many sexual assaults from an intimate partner compared to IPV-only women. The number of adverse events contributed significantly to variance in trauma symptoms over and above that of exposure to IPV alone. Women exposed to additional events had approximately twice as many avoidance and physiological arousal symptoms as IPV-only women. Conclusions: The results of this study suggest a variety of implications for IPV treatment and interventions. Specifically, the role that additional interpersonal violence, especially sexual violence, plays in the expression of distress may relate to the type of service offered to the survivor. (PsycINFO Database Record (c) 2011 APA, all rights reserved)     

Antecedents and consequences of satisfaction and commitment in turnover models: A reanalysis using latent variable structural equation methods.

A review of recent models of organizational commitment (e.g., J. H. Morris and J. D. Sherman; see record 1981-33773-001) and turnover (e.g., W. H. Mobley et al; see record 1979-29973-001) indicates that the causal relation between job satisfaction and organizational commitment had been overlooked and that attempts to identify the antecedents of these variables had suffered from conceptual and methodological limitations. To examine these 2 issues, structural equation methodology was used to reanalyze path analysis data from C. E. Michaels and P. E. Spector (see record 1982-10938-001) and A. C. Bluedorn (see record 1982-22265-001). Four causal models were examined. Across both samples, support was obtained for relations between personal/organizational characteristics and job satisfaction and between satisfaction and commitment. Commitment was also an important determinant of turnover intentions. Results suggest that the path analysis technique does not allow for the simultaneous examination of the effects of exogenous variables on 2 or more endogenous variables. (44 ref) (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

The male role, alcohol use, and alcohol problems: A structural modeling examination in adult women and men.

Most research on sex differences in alcohol involvement suggests that drinking is a component of the male gender role, but the impact of specific male role factors on alcohol involvement has not yet been studied. The authors used structural modeling to examine the relationships among 3 male role variables (agency, traditional male role attitudes, and masculine gender role stress), alcohol consumption, and alcohol-related problems in a sample of women and men. To determine whether sex moderates this relationship, models were computed separately for men and women. For men, traditional attitudes led to more alcohol consumption, whereas agentic traits protected them from experiencing alcohol-related problems, and experiencing masculine gender role stress was a risk factor for these problems. Male role variables were unrelated to women's alcohol consumption, but women who believed more in the traditional role of men suffered from more alcohol-related problems. Discussion centers on the contribution of components of the male role on alcohol outcomes as well as the different implications for men and women. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Personal space: The conceptual and measurement implications of structural equation models.

Investigated the stop-distance procedure for measuring personal space, using maximum likelihood estimation of structural equation models. Three data sets previously described by the author (see PA, Vols 67:5708 and 68:1091) were examined. Results challenge the factor model underlying recent estimates of the reliability of the stop-distance procedure and convincingly demonstrate the reliability of stop-distance measurements. About 97% of the variance in observed distances arose from sources other than structural measurement error. About 8% of the variance in measured distances was due to sources that reflected unidentified causal determinants of spacing. The repeated failures of the factor model and the repeated successes of the simplex model require a fundamental shift in the conceptualization of personal space. The failure of the factor model implies that momentary spatial preferences should not be considered as merely reflecting a stable underlying preference or as a repeated and momentary construction based on stable situational features. Personal space should be considered as a dynamic process that is continually open to modification but that shows considerable stability due to the persistence of previously maintained distances. (French abstract) (12 ref) (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Alcohol use and intimate partner violence perpetration among college students: Assessing the temporal association using electronic diary technology.

Objectives: The primary goals of this study were to assess the temporal relationship between alcohol use and intimate partner violence (IPV) perpetration using state-of-the-art electronic diary assessment methods and to examine the extent to which distal factors (e.g., sex, psychopathology, relationship satisfaction) moderated that association. Method: Participants were 184 male and female college students in dating relationships who used a handheld computer to answer daily questions about alcohol use and IPV every day for 2 months. Results: Based on a total of 7,775 daily electronic diary reports, results showed that the odds of perpetrating psychological and physical aggression were 2.19 and 3.64 times greater, respectively, on drinking days relative to nondrinking days. Men evidenced 7.03 greater odds of engaging in psychological aggression on drinking days, whereas women had only 1.60 greater odds of engaging in psychological aggression on drinking relative to nondrinking days. Conclusion: Findings suggest the need to provide intervention early in dating relationships to reduce alcohol use to reduce the risk of IPV. (PsycINFO Database Record (c) 2011 APA, all rights reserved)     

What men want: The role of reflective opposite-sex normative preferences in alcohol use among college women.

Misperceptions of peer drinking norms have been found to be strongly associated with individual drinking behavior, especially for proximal reference groups such as same-sex friends. Less studied are the effects of perceived preferences from the opposite sex on alcohol use; that is, the behaviors an individual believes the opposite sex prefers from them. Research suggests that these perceived “reflective” normative preferences may be particularly salient among college women, who may drink in pursuit of intimate relationships and positive attention from male peers. Heterosexual undergraduate students from two universities participated in this project. Females answered questions regarding the amount of alcohol they believe a typical male would like his female friends, dates, or romantic partners to drink. Males answered the same questions, stating their actual preferences. Results showed that females overestimate the amount of alcohol males want their female friends, dating partners, and sexual partners to drink, and that this misperception was associated with their drinking behavior, even after controlling for perceived same-sex norms. These results suggest that reflective normative feedback may offer a powerful new tool for female-targeted interventions. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Separating trait effects from trait-specific method effects in multitrait-multimethod models: A multiple-indicator CT-C(M-1) model.

An overview of several models of confirmatory factor analysis for analyzing multitrait-multimethod (MTMM) data and a discussion of their advantages and limitations are provided. A new class of multi-indicator MTMM models combines several strengths and avoids a number of serious shortcomings inherent in previously developed MTMM models. The new models enable researchers to specify and to test trait-specific-method effects. The trait and method concepts composing these models are explained in detail and are contrasted with those of previously developed MTMM models for multiple indicators. The definitions of the models are explained step by step, and a practical empirical application of the models to the measurement of 3 traits x 3 methods is used to demonstrate their advantages and limitations. (PsycINFO Database Record (c) 2010 APA, all rights reserved)