Fit Indices Of Structural Equation Model Research Articles

Mediators of dietary diversity score (DDS) on NAFLD in Iranian adults: a structural equation modeling study.

The current study examines the association between the Dietary Diversity Score (DDS) and nonalcoholic fatty liver disease (NAFLD) in Iranian adults using structural equation modeling (SEM). A sample of 3220 adults from the Amol Cohort Study was recruited for this cross-sectional study. Dietary acid load (DAL) and DDS were calculated using the data obtained from a validated food frequency questionnaire. Anthropometric parameters, blood pressure, biochemical measurements, and liver ultrasonography were evaluated according to standard protocols. DDS was neither directly nor indirectly associated with a greater prevalence of NAFLD. In the second model (DDS sub-scores model), the association of DAL with NAFLD was fully mediated through waist circumference (WC) (of DAL to WC: β = 0.14, P < 0.0001, and of WC to NAFLD: β = 0.50, P < 0.001). Vegetable and fruit diversity scores had a significant negative indirect relationship with NAFLD prevalence through DAL (β = -0.06, P = 0.001, β = -0.10, P < 0.001, respectively). Meat diversity score was positively associated with NAFLD prevalence in a full mediational process through DAL (β = 0.12, P < 0.001). The SEM fit indices suggested a reasonably adequate fit of the data to the DDS model (Χ2/df = 4.76, GFI = 0.98, AGFI = 0.97, IFI = 0.97, CFI = 0.97, RMSEA = 0.03, and SRMR = 0.02) and its sub-scores model (Χ2/df = 4.72, GFI = 0.98, AGFI = 0.97, IFI = 0.95, CFI = 0.95, RMSEA = 0.03, and SRMR = 0.02). Meat diversity and lack of vegetable and fruit diversity were indirectly associated with NAFLD prevalence through DAL and WC mediators. Interventions for NAFLD may be more successful if they target a lower intake of animal protein sources and dietary diversity, particularly vegetable and fruit diversity.

Presenting a Model of Co-Dependency in Women with Addicted Spouses based on their Self-Differentiation with the Mediating Role of Emotional Cognitive Regulation

Aim: The aim of this study was to present a model of co-dependency in women with addicted spouses based on their differentiation with the mediating role of emotional cognitive regulation. Methods: The research method is cross-sectional correlation. The statistical population of this study consisted of all women with drug-addicted wives who referred to counseling centers, health centers and addiction treatment camps and meetings in Tehran in 1400, of which 188 people by cluster sampling they were selected in stages. In this study, tools of co-dependency (Span &amp; Fisher, 1990), self-differentiation (Skorn and Friedlander, 1998) and cognitive-emotional regulation (Garnfsky and Craig, 2006) were used. Amos-V8.8 software were used to analyze the data. Structural equation modeling was also used to answer the research hypotheses. Findings showed that the model has a good fit. Results: The results also showed that self-differentiation had a significant direct negative effect on co-dependency (P &lt;0.01). Self-differentiation had a direct positive effect on adaptive cognitive emotion regulation strategies (P &lt;0.01). Adaptive strategies for cognitive emotion regulation have a direct and negative effect on co-dependency (P &lt;0.01). The results showed that non-adaptive cognitive emotion regulation strategies had a direct and positive effect on co-dependency (P &lt;0.01). Self-differentiation also had an indirect effect on codependency through cognitive emotion regulation (β = -0.181; P = 0.01). Conclusion: Structural equation modeling fit indices confirmed the overall research model and the direct and indirect effects between the research variables were confirmed. Therefore, according to the results, it can be said that co-dependency is an important variable in predicting self-differentiation and cognitive regulation of emotion.

A Resilience Model for Patients With Colorectal Cancer: A Structural Equation Modeling Analysis.

Patients with colorectal cancer (CRC) experience multiple symptoms. Resilience is a positive health outcome that can assist patients to face and adapt to their disease. The purpose of this study was to evaluate a proposed resilience model for patients with CRC. Patients (n = 416), who were given a diagnosis of stage Ι to III CRC within the past 5 years, were recruited from 2 medical centers in Northern Taiwan. Symptom Severity Scale, Fatigue Symptom Inventory, and Center for Epidemiological Studies Depression scale were used to assess the risk factors of symptom severity, fatigue, and depressive symptoms, respectively. Cancer Behavior Inventory and Functional Assessment of Chronic Illness Therapy-Spiritual Well-Being Scale were used to assess the protective factors of self-efficacy for coping with cancer and spiritual well-being, respectively. Resilience was assessed using the Resilience Scale. Structural equation modeling was used to evaluate the proposed resilience model for patients with CRC. The initial structural equation modeling fit indices did not support the proposed model. In the revised model, depressive symptoms was a partial mediator between protective factors and resilience with an acceptable model fit (comparative fit index, 0.968; root mean square error of approximation, 0.085; standardized root mean square residual, 0.034). Patients with CRC who had higher levels of protective factors had higher levels of resilience. This study provides new information on the role of depressive symptoms as a partial mediator between protective factors and resilience. Oncology nurses need to evaluate for depressive symptoms as well as protective factors and resilience in patients with CRC.

The Effect of Estimation Methods on SEM Fit Indices.

We examined the effect of estimation methods, maximum likelihood (ML), unweighted least squares (ULS), and diagonally weighted least squares (DWLS), on three population SEM (structural equation modeling) fit indices: the root mean square error of approximation (RMSEA), the comparative fit index (CFI), and the standardized root mean square residual (SRMR). We considered different types and levels of misspecification in factor analysis models: misspecified dimensionality, omitting cross-loadings, and ignoring residual correlations. Estimation methods had substantial impacts on the RMSEA and CFI so that different cutoff values need to be employed for different estimators. In contrast, SRMR is robust to the method used to estimate the model parameters. The same criterion can be applied at the population level when using the SRMR to evaluate model fit, regardless of the choice of estimation method.

Role of ADHD in risky riding behavior: a statistical modeling

Attention Deficiency and Hyperactivity Disorder (ADHD), as a predictor of injuries in motorcyclists, affects the risky behavior. Since there was no pre-established conceptual model, this study aimed at exploring a conceptual model. Following this model, the Structural Equation Modeling (SEM) was utilized to find the predictors of Motorcycle Riding Behavior (MRB), as well as the mediators and moderators of ADHD-MRB relationship. In the current cross-sectional study, 340 motorcyclists in Bukan city, Iran, were recruited through a randomized cluster sampling. A simple conceptual model was explored and utilizing the goodness of fit indices in SEM, an optimal model was chosen. Then, utilizing 3-step hierarchical regressions and SEMs, the relationship between ADHD and MRB was assessed by modeling the possible mediators/moderators such as answering the cell phone and using the helmet. The results of hierarchical regression showed that answering the cell phone had both moderating and mediating effects on the relationship between ADHD (and the ASS subscale) with MRB. The final SEM, by introducing the mediating role of underlying variables, had a good fit on data (Normed Chi2 = < 5.0, RMSEA < 0.08, SRMR < 0.05, CFI and TLI > 0.90), wherein ADHD score (and the subscales) predicted the MRB score directly/indirectly (P < 0.05). A simple conceptual model was found to assess the mediating role of ADHD in motorcyclist risky behavior. Based upon the findings, training the techniques of and/or enforcement for controlling and improving riding behaviors and skills among ADHD motorcyclists, those who answer their cell phones while riding, un-experienced riders, and those who ride without wearing the helmet is strongly recommended.

Relative Effects at Work

Assessing the relative importance of predictors has been of historical importance in a variety of disciplines including management, medicine, economics, and psychology. When approaching hypotheses on the relative ordering of the magnitude of predicted effects (e.g., the effects of discrimination from managers and coworkers are larger than that from clients), one quickly runs into problems within a traditional frequentist framework. Null hypothesis significance testing does not allow researchers to directly map research hypotheses on to results and suffers from a multiple testing problem that leads to low statistical power. Furthermore, all traditional structural equation modeling fit indices lose much of their suitability for model comparison, because order hypotheses are not countable in terms of degrees of freedom. To adequately tackle order hypotheses, we advocate a Bayesian method that provides a single internally consistent solution for estimation and inference. The key element in the proposed model comparison approach is the use of the Bayes factor and the incorporation of order constraints by means of a smart formulation of prior distributions. An easy-to-use software package BIEMS (Bayesian inequality and equality constrained model selection) is introduced and two empirical examples in the organizational behavior area are provided to showcase the method, both offering new findings that have implications for theory: the first on the differential impact of discrimination in the workplace from insiders and outsiders to the organization on employees’ well-being, and the second on Karasek’s stressor–strain theory about how the relative order of magnitude of the effects of job control and demands depends on the specific well-being outcome dimension.

Multidimensionality and Structural Coefficient Bias in Structural Equation Modeling

In this study, the authors consider several indices to indicate whether multidimensional data are “unidimensional enough” to fit with a unidimensional measurement model, especially when the goal is to avoid excessive bias in structural parameter estimates. They examine two factor strength indices (the explained common variance and omega hierarchical) and several model fit indices (root mean square error of approximation, comparative fit index, and standardized root mean square residual). These statistics are compared in population correlation matrices determined by known bifactor structures that vary on the (a) relative strength of general and group factor loadings, (b) number of group factors, and (c) number of items or indicators. When fit with a unidimensional measurement model, the degree of structural coefficient bias depends strongly and inversely on explained common variance, but its effects are moderated by the percentage of correlations uncontaminated by multidimensionality, a statistic that rises combinatorially with the number of group factors. When the percentage of uncontaminated correlations is high, structural coefficients are relatively unbiased even when general factor strength is low relative to group factor strength. On the other hand, popular structural equation modeling fit indices such as comparative fit index or standardized root mean square residual routinely reject unidimensional measurement models even in contexts in which the structural coefficient bias is low. In general, such statistics cannot be used to predict the magnitude of structural coefficient bias.

Testing a Model of Delayed Care-Seeking for Acute Myocardial Infarction

A theory-testing approach to the study of delay in seeking treatment for acute myocardial infarction (AMI) was performed using a descriptive design with 135 AMI patients. Participants provided information pertaining to history of AMI, symptom congruence, responses to symptoms, cardiac symptom attribution, and AMI care-seeking delay. Structural equation modeling fit indices suggested that the independent predictors of AMI care-seeking delay were cardiac symptom attribution and emotion-focused coping. History of AMI had a direct relationship with AMI care-seeking delay, but its total effect through symptom attribution and symptom congruence was not significant. The total effect of symptom congruence on AMI care-seeking delay was significant. In conclusion, the study findings highlight the importance of targeting cardiac symptom attribution and emotion-focused coping in interventions that are aimed at reducing AMI care-seeking delay.

The Theory of Planned Behavior: Predicting Physical Activity and Cardiorespiratory Fitness in African American Children

The purpose of our study was to evaluate the ability of the Theory of Planned Behavior (TPB) to predict African American children’s moderate to vigorous physical activity (MVPA) and cardiorespiratory fitness. Children (N = 548, ages 9–12) completed questionnaires assessing the TPB constructs and MVPA and then had their cardiorespiratory fitness assessed with the Progressive Aerobic Cardiovascular Endurance Run (PACER) test. Commonly used Structural Equation Modeling fit indices suggested the model was an adequate representation for the relationships within the data. However, results also suggested an extended model which was examined and supported. Tests of direct paths from subjective norm and control to intention indicated that both variables were significant predictors of intention. Furthermore, the impact of attitude on intention was mediated by both subjective norm and control. Finally MVPA predicted cardiorespiratory fitness. Most of the standardized path coefficients fell in the small to moderate range, with the strongest effects evident for the predictors of intention and the smallest effect evident for the link from MVPA to cardiorespiratory fitness.

The Noncentral Chi-square Distribution in Misspecified Structural Equation Models: Finite Sample Results from a Monte Carlo Simulation

The noncentral chi-square distribution plays a key role in structural equation modeling (SEM). The likelihood ratio test statistic that accompanies virtually all SEMs asymptotically follows a noncentral chi-square under certain assumptions relating to misspecification and multivariate distribution. Many scholars use the noncentral chi-square distribution in the construction of fit indices, such as Steiger and Lind's (1980) Root Mean Square Error of Approximation (RMSEA) or the family of baseline fit indices (e.g., RNI, CFI), and for the computation of statistical power for model hypothesis testing. Despite this wide use, surprisingly little is known about the extent to which the test statistic follows a noncentral chi-square in applied research. Our study examines several hypotheses about the suitability of the noncentral chi-square distribution for the usual SEM test statistic under conditions commonly encountered in practice. We designed Monte Carlo computer simulation experiments to empirically test these research hypotheses. Our experimental conditions included seven sample sizes ranging from 50 to 1000, and three distinct model types, each with five specifications ranging from a correct model to the severely misspecified uncorrelated baseline model. In general, we found that for models with small to moderate misspecification, the noncentral chi-square distribution is well approximated when the sample size is large (e.g., greater than 200), but there was evidence of bias in both mean and variance in smaller samples. A key finding was that the test statistics for the uncorrelated variable baseline model did not follow the noncentral chi-square distribution for any model type across any sample size. We discuss the implications of our findings for the SEM fit indices and power estimation procedures that are based on the noncentral chi-square distribution as well as potential directions for future research.

Effects of Potential Confounding Factors on Fit Indices and Parameter Estimates for True and Misspecified SEM Models

The present Monte Carlo study assessed the effects of three potential confounding factors on structural equation modeling (SEM) fit indices and parameter estimates: data nonnormality, estimation method, and sample size. The major findings were that (a) relatively mild data nonnormality has little effect on SEM fit indices and parameter estimates; (b) under misspecified models, estimation method (maximum likelihood [ML] vs. generalized least squares [GLS]) has considerable influence on SEM incremental fit indices; and (c) some fit indices are more susceptible to the influence of sample size. Previous findings in the literature that SEM fit indices were consistent under different estimation methods may need to be revisited, because the finding was primarily based on Monte Carlo simulations involving true SEM models. Because SEM researchers rarely are certain whether they have correctly specified their models, it is critical that simulation studies are conducted in the presence of model misspecification, as in the present study.

Effects of estimation methods, number of indicators per factor, and improper solutions on structural equation modeling fit indices

(1995). Effects of estimation methods, number of indicators per factor, and improper solutions on structural equation modeling fit indices. Structural Equation Modeling: A Multidisciplinary Journal: Vol. 2, No. 2, pp. 119-143.