Covariance Structure Models Research Articles

Make Some Noise: Generating Data from Imperfect Factor Models

Researchers simulating covariance structure models sometimes add model error to their data to produce model misfit. Presently, the most popular methods for generating error-perturbed data are those by Tucker, Koopman, and Linn (TKL), Cudeck and Browne (CB), and Wu and Browne (WB). Although all of these methods include parameters that control the degree of model misfit, none can generate data that reproduce multiple fit indices. To address this issue, we describe a multiple-target TKL method that can generate error-perturbed data that will reproduce target RMSEA and CFI values either individually or together. To evaluate this method, we simulated error-perturbed correlation matrices for an array of factor analysis models using the multiple-target TKL method, the CB method, and the WB method. Our results indicated that the multiple-target TKL method produced solutions with RMSEA and CFI values that were closer to their target values than those of the alternative methods. Thus, the multiple-target TKL method should be a useful tool for researchers who wish to generate error-perturbed correlation matrices with a known degree of model error. All functions that are described in this work are available in the fungible R library. Additional materials (e.g., R code, supplemental results) are available at https://osf.io/vxr8d/.

Adventitious Error and Its Implications for Testing Relations Between Variables and for Composite Measurement Outcomes

Wu and Browne (Psychometrika 80(3):571–600, 2015. https://doi.org/10.1007/s11336-015-9451-3; henceforth W &B) introduced the notion of adventitious error to explicitly take into account approximate goodness of fit of covariance structure models (CSMs). Adventitious error supposes that observed covariance matrices are not directly sampled from a theoretical population covariance matrix but from an operational population covariance matrix. This operational matrix is randomly distorted from the theoretical matrix due to differences in study implementations. W &B showed how adventitious error is linked to the root mean square error of approximation (RMSEA) and how the standard errors (SEs) of parameter estimates are augmented. Our contribution is to consider adventitious error as a general phenomenon and to illustrate its consequences. Using simulations, we illustrate that its impact on SEs can be generalized to pairwise relations between variables beyond the CSM context. Using derivations, we conjecture that heterogeneity of effect sizes across studies and overestimation of statistical power can both be interpreted as stemming from adventitious error. We also show that adventitious error, if it occurs, has an impact on the uncertainty of composite measurement outcomes such as factor scores and summed scores. The results of a simulation study show that the impact on measurement uncertainty is rather small although larger for factor scores than for summed scores. Adventitious error is an assumption about the data generating mechanism; the notion offers a statistical framework for understanding a broad range of phenomena, including approximate fit, varying research findings, heterogeneity of effects, and overestimates of power.

Direct Discrepancy Dynamic Fit Index Cutoffs for Arbitrary Covariance Structure Models

Despite the popularity of traditional fit index cutoffs like RMSEA ≤ .06 and CFI ≥ .95, several studies have noted issues with overgeneralizing traditional cutoffs. Computational methods have been proposed to avoid overgeneralization by deriving cutoffs specifically tailored to the characteristics of the model being evaluated. Simulations show favorable performance of these methods; however, these methods support a narrow set of scenarios (e.g., certain models or response scales) and the interpretation of cutoffs is not always standardized, which affects empirical researchers’ ability to confidently and broadly adopt these methods to evaluate model fit. In this paper, we propose an extension to one recently developed computational method—dynamic fit index cutoffs—that (a) permits application to any covariance structure model (e.g., CFA, mediation, bifactor), (b) standardizes interpretation of cutoffs across any covariance structure model, and (c) supports normal, nonnormal, categorical, and missing data. Software is provided to facilitate implementation of the method.

THE INFLUENCE OF QUALITY SERVICE ON CUSTOMER SATISFACTION: THE MEDIATING ROLE OF CULTURAL INTELLIGENCE IN SOME SELECTED BANKS IN JOS NORTH LGA, PLATEAU STATE.

The complaining attitudes of customers about poor service delivery in most Nigeria banks posed a great concern to so many Nigerians. Most customers complain of the unfriendly attitude and nonchalant dispositions of so many bank workers, as the performance of most staff is below the expectations of so many customers patronizing the organization. Based on this, the study therefore aims to evaluate how the role of cultural intelligence in mediating the relationship between service quality and customer satisfaction among some selected banks in Jos North LGA of Plateau State. The total population of 562 staff of the selected banks was used for the study. The use of questionnaire was adopted as the primary method of data collection, administered to the sample size of 234 staff out of which 230 was duly completed and retrieved. Co-variance Structural equation modeling was used in analyzing the data. From the result, hypothesis one was tested and it was discovered that there is a significant relationship between service quality and customer satisfaction. Hypothesis two also showed that there is a significant relationship between service quality and cultural intelligence. Hypothesis three showed a significant relationship between cultural intelligence and customer satisfaction, and finally hypothesis four shows that cultural intelligence mediates the relationship between service quality and customer satisfaction. This study concluded that cultural intelligence which has to do with the ability of employees to understand the various cultures, beliefs, norms, and values of customers goes a long way in adding value to the level of service quality of the bank which goes a long way in enhancing customer satisfaction in the selected banks. The study recommended that employees are to be culturally intelligent enough to manage customers by valuing the individual cultural diversity and also treat them as such. This will go a long way in encouraging customers to stay with the banks.

Analysis of the community responses to road traffic noise using structural equation modeling -comparison of the covariance structure models for different housing types-

As for the situation of road traffic noise problems in Japan, the percentage of areas where achieve the environmental quality standards for road traffic noise tends to increase year by year. On the other hand, number of complains about road traffic noise has not been changed recent years. In order to determine the factors affecting annoyance due to road traffic noise, we analyzed how the annoyance was determined using the dataset derived from a social survey on community response. The social survey was conducted along arterial roads in 2019 and 2020. Total sample sizes were 360 and 228 in detached houses and apartments, respectively. Noise exposure was estimated based on the ASJ RTN-Model. We constructed a covariance structure model which represents the hierarchical structure from noise exposure to annoyance via activity disturbances and applied multiple-group analysis for structural equation modeling to the model. This paper focused on the difference in the direct and indirect impacts of noise exposure on annoyance between the detached houses and apartments. The analysis showed that the determination of annoyance which was affected by noise exposure via activity disturbances differed according to housing types.

Exploring the Nexus between Transparency and Citizens’ Intention to Participate in Climate Change Policy-Making

This study aims to explore strategies that can propel informed and inclusive citizen engagement in shaping climate policy that addresses the formidable challenge of climate change and shapes a more sustainable future for all. To this end, the researcher endeavored to unpack the complex interplay and mechanisms at play in this relationship through an in-depth investigation into the four mediating factors, efficacy, awareness, concern, and attitude, and four pathways that link transparency to citizen intentions to participate in climate policy-making. The researcher constructed a conceptual model with mediators and serial multi-mediators that incorporates relationships between variables based on research hypotheses. To test these research hypotheses and estimate the conceptual model, structural equation modeling (SEM) and phantom models representing specific indirect effects of the covariance structure model were applied, .using AMOS Ver. 26.0. The sample consisted of 500 adults selected through a proportionate stratified sample design. Research findings confirmed that the overall fit of this research model was deemed appropriate, and the direct effect and indirect effect of transparency on citizens’ intention to participate in climate change policy-making is confirmed. Based on model fit, the researcher proposed a Transparency–Engagement Nexus Model that shows the relationship between transparency and citizens’ intention to participate in climate change policy-making. The theoretical and practical implications of these research findings were addressed, and future research directions were also suggested.

Safe Destination Choice Among Tourism-Product Consumers in the New Era of Tourism

The current study assessed and demonstrated the impact of perceived knowledge and perceived susceptibility about COVID-19 on travelers’ intentions for safe destination choice in case when the COVID-19 pandemic is being controlled by crowdedness (i.e., human crowdedness and spatial crowdedness) and monetary promotions. The reliability and validity of the proposed research model were tested by using regression analysis and covariance structural equation modeling. The results revealed a significant effect of perceived knowledge and perceived susceptibility on behavioral intention. It was evidenced that increasing knowledge and susceptibility of COVID-19 is necessary. The moderating effects of human crowdedness, spatial crowdedness, and monetary promotions were also examined through SPSS Process Macro v3.5 and invariance test. In addition, differences in demographic variables (gender, age, annual income, marital status, and ethnic background) on the research model were unveiled. Lastly, both theoretical values and practical implications of this study were discussed.

Predictors of Viral Load and Medication Adherence Among HIV-Positive Adults Under Treatment at Felege-Hiwot Comprehensive Specialized Hospital, North-West, Ethiopia.

Maintaining good medication adherence and decreasing viral load in patients living with HIV/AIDS are critical to ensuring antiretroviral therapy's preventive and therapeutic benefits. The main objective of this study was to assess the predictors of viral load and medication adherence among HIV-positive adults under treatment at Felege Hiwot Comprehensive Specialized Hospital (FHCSH). A retrospective cohort study design was conducted from a random sample of 281 adult HIV-infected patients under treatment at FHCSH in northwest Ethiopia from June 2017 to June 2021. Separate GLMM was used in analysis of viral load and medication adherence, and joint mode was applied to fit those two outcomes jointly. The potential correlation of those two outcomes was linked by random intercepts. Information criteria (AIC and BIC) were used for model comparison and covariance structure selection. The small standard error of significant predictors and significant correlation between viral load and medication adherence over time provide evidence for joint model selection. The correlation between viral load and medication adherence was -0.7688 (P-value=< 0.05), which indicates that the decrement of viral load tends to increase good medication adherence. Patient substance use, visit time, baseline CD4 cell, baseline hemoglobin, and the interaction of visit time by substance use were significantly associated with viral load and medication adherence jointly. The study revealed that substance user adult patients, patients with low baseline CD4 cells, and patients with low baseline hemoglobin were with high viral loads and poor medication adherence. Therefore, health officials and other concerned bodies should give special attention and high intervention to patients with low baseline hemoglobin; poor adherence and low baseline CD4 cell count.

A model-based approach to multivariate principal component regression: Selecting principal components and estimating standard errors for unstandardized regression coefficients.

Principal component regression (PCR) is a popular technique in data analysis and machine learning. However, the technique has two limitations. First, the principal components (PCs) with the largest variances may not be relevant to the outcome variables. Second, the lack of standard error estimates for the unstandardized regression coefficients makes it hard to interpret the results. To address these two limitations, we propose a model-based approach that includes two mean and covariance structure models defined for multivariate PCR. By estimating the defined models, we can obtain inferential information that will allow us to test the explanatory power of individual PCs and compute the standard error estimates for the unstandardized regression coefficients. A real example is used to illustrate our approach, and simulation studies under normality and nonnormality conditions are presented to validate the standard error estimates for the unstandardized regression coefficients. Finally, future research topics are discussed.

Assessing an alternative for "negative variance components": A gentle introduction to Bayesian covariance structure modeling for negative associations among patients with personalized treatments.

The multilevel model (MLM) is the popular approach to describe dependences of hierarchically clustered observations. A main feature is the capability to estimate (cluster-specific) random effect parameters, while their distribution describes the variation across clusters. However, the MLM can only model positive associations among clustered observations, and it is not suitable for small sample sizes. The limitation of the MLM becomes apparent when estimation methods produce negative estimates for random effect variances, which can be seen as an indication that observations are negatively correlated. A gentle introduction to Bayesian covariance structure modeling (BCSM) is given, which makes it possible to model also negatively correlated observations. The BCSM does not model dependences through random (cluster-specific) effects, but through a covariance matrix. We show that this makes the BCSM particularly useful for small data samples. We draw specific attention to detect effects of a personalized intervention. The effect of a personalized treatment can differ across individuals, and this can lead to negative associations among measurements of individuals who are treated by the same therapist. It is shown that the BCSM enables the modeling of negative associations among clustered measurements and aids in the interpretation of negative clustering effects. Through a simulation study and by analysis of a real data example, we discuss the suitability of the BCSM for small data sets and for exploring effects of individualized treatments, specifically when (standard) MLM software produces negative or zero variance estimates. (PsycInfo Database Record (c) 2021 APA, all rights reserved).

비합리적 신념과 우울 간의 관계에서 자기혐오의 매개효과

Objectives The purpose of this study is to investigate the relations among irrational beliefs, depression, and self-disgust, and determine the mediating role of self-disgust in the relationship between irrational beliefs and depression.&#x0D; Methods Data for this research were collected by conducting an online survey nationwide with 397 respondents (male 149 and female 248) ranging from their 20s to 60s, and the mediating effect was examined through the covariance structure model analysis.&#x0D; Results The The main results of this study are summarized as follows. First, it turned out that irrational beliefs such as demandingness, catastrophizing, frustration intolerance, and self-downing have a positive influence on depression. Second, it was demonstrated that self-disgust serves as a partial mediator associations between demandingness, catastrophizing, frustration intolerance and depression. Third, self-disgust proved to function as a full mediator between self-downing and depression.&#x0D; Conclusions On the basis of the results, the meanings of the study and the implications for more effective interventions for depression treatment in terms of cognitive behavioral therapy are discussed, and suggestions for further research are proposed.

EFFECT OF SERVICE QUALITY DELIVERY AND CUSTOMER SATISFACTON ON CUSTOMER LOYALTY IN SOME SELECTED HOSPITALS IN JOS METROPOLIS

The study evaluated the effect of service quality delivery and customer satisfaction on customer loyalty in selected hospitals in Jos North Metropolis. The main objective of the study was to ascertain the extent to which customer satisfaction mediates the relationship between service quality and customer loyalty in selected hospitals in Jos North Metropolis. The total populations of 456,568 customers of the selected hospitals were used for the study. The study adopted survey method of research with the use of questionnaire to collect data from 400 sampled customers, out of which 360 were duly completed and retrieved. Simple random sampling technique was adopted for the study while Co-variance Structural Equation Modeling (CB-SEM) was used in analyzing the data. From the results, hypothesis one, two and three were tested and it was found that there are significant relationship between service quality delivery and customer loyalty, there is a significant relationship between service quality delivery and customer satisfaction, there is a significant relationship between customer satisfaction and customer loyalty respectively. It was confirmed that customer satisfaction mediates the relationship between service quality delivery and customer loyalty. The study concluded that service quality delivery alone does not ensure long term loyalty of customers but paying attention to customer satisfaction in any organization will further ensure effective customer loyalty. The study recommended that health service organizations should recognized that in the midst of competition, service quality delivery is necessary to sustain loyalty, but where quality is given and satisfaction is not sustained, the tendency of loyalty of such customer will be very low since customers are rational beings; therefore, the study further recommends that health organizations should build up the satisfaction level of their customers by improving on their services, this will go a long way in strengthening the relationship between service quality delivery and customer loyalty.

Statistical Inference in Redundancy Analysis: A Direct Covariance Structure Modeling Approach

Redundancy analysis (RA) is a multivariate method that maximizes the mean variance of a set of criterion variables explained by a small number of redundancy variates (i.e., linear combinations of a set of predictor variables). However, two challenges exist in RA. First, inferential information for the RA estimates might not be readily available. Second, the existing methods addressing the dimensionality problem in RA are limited for various reasons. To aid the applications of RA, we propose a direct covariance structure modeling approach to RA. The proposed approach (1) provides inferential information for the RA estimates, and (2) allows the researcher to use a simple yet practical criterion to address the dimensionality problem in RA. We illustrate our approach with an artificial example, validate some standard error estimates by simulations, and demonstrate our new criterion in a real example. Finally, we conclude with future research topics.

The longitudinal effects of education on depression: Finding from the Indonesian national survey.

A thorough and continuous investigation of the association between education and depression in Southeast Asia is critical, particularly in Indonesia, where depression is highly prevalent. Despite this, studies on education and depression mainly use a cross-sectional design alone, which cannot control the bidirectionality of the relationship. Therefore, this study investigated the longitudinal effects of education on depression symptoms, based on nationally representative survey data. This study used as its basis a longitudinal socioeconomic and health survey in Indonesia, the Indonesia Family Life Survey (IFLS). The survey collected data through face-to-face interviews with individual respondents and their families. The fourth and fifth waves of IFLS datasets were used in the analysis. A total number of 18,374 adult participants were included in the dataset. Depression symptoms were assessed based on a 10-item version of the CES-D (Center for Epidemiologic Studies Depression) Scale. Education level was the highest level of education attained by the participants. A cross-lagged longitudinal model was tested using structural equation modeling (SEM) or analysis of covariance structure. The results showed that the model of education and depression fits the data well. The fit indices of the model, χ2 (1, N = 18,374) = 21.592, p = 0.001, RMSEA = 0.033, CFI =. 0999, fulfilled the requirements for a good fit. Meanwhile, further analysis of the cross-lagged model revealed that education predicted depression and not the other way around. The standardized regression weights showed that higher education attainment reduces the risk of depression later in life. This study asserts that educational attainment has longitudinal effects on depression. Therefore, expanding the policies surrounding educational opportunity may prevent the onset of depression. This is important, especially in the Indonesian context, where the prevalence of depression among adults is higher than the global average. Access to further education deserves continued consideration in research and policy discussions on mental health and educational system development.

Parsimonious genotype by environment interaction covariance models for cassava (Manihot esculenta).

The assessment of cassava clones across multiple environments is often carried out at the uniform yield trial, a late evaluation stage, before variety release. This is to assess the differential response of the varieties across the testing environments, a phenomenon referred to as genotype-by-environment interaction (GEI). This phenomenon is considered a critical challenge confronted by plant breeders in developing crop varieties. This study used the data from variety trials established as randomized complete block design (RCBD) in three replicates across 11 locations in different agro-ecological zones in Nigeria over four cropping seasons (2016–2017, 2017–2018, 2018–2019, and 2019–2020). We evaluated a total of 96 varieties, including five checks, across 48 trials. We exploited the intricate pattern of GEI by fitting variance–covariance structure models on fresh root yield. The goodness-of-fit statistics revealed that the factor analytic model of order 3 (FA3) is the most parsimonious model based on Akaike Information Criterion (AIC). The three-factor loadings from the FA3 model explained, on average across the 27 environments, 53.5% [FA (1)], 14.0% [FA (2)], and 11.5% [FA (3)] of the genetic effect, and altogether accounted for 79.0% of total genetic variability. The association of factor loadings with weather covariates using partial least squares regression (PLSR) revealed that minimum temperature, precipitation and relative humidity are weather conditions influencing the genotypic response across the testing environments in the southern region and maximum temperature, wind speed, and temperature range for those in the northern region of Nigeria. We conclude that the FA3 model identified the common latent factors to dissect and account for complex interaction in multi-environment field trials, and the PLSR is an effective approach for describing GEI variability in the context of multi-environment trials where external environmental covariables are included in modeling.

On the Entrepreneurial Intention and Entrepreneurial Behavior Path of College Students Based on the Theory of Planned Behavior

It is of practical significance to explore the mechanism of entrepreneurship education on college students’ entrepreneurial intention, as it can provide reference for the innovations in college students’ entrepreneurial ability training mode and the formulation of relevant supporting policies. At present, the relevant research on the influence mechanism of entrepreneurship education on college students’ entrepreneurial intention is not deep enough and lacks relevant empirical analysis, which has led to great differences in the empirical results. Therefore, this paper explores the entrepreneurial intention and behavior path of college students based on the theory of planned behavior. First, an analysis framework of the core elements of entrepreneurial intention was built based on the theory of planned behavior, and the core elements were also analyzed. Then, a measurement model of college students’ entrepreneurial intention was constructed, and the contingent value method was introduced to study college students’ entrepreneurial intention. A schematic diagram of the path relationship of college students’ entrepreneurial behaviors was also given, and the covariance structural equation model for all the specific elements was constructed. The rationality of the model was verified, and how the different core elements of the model are correlated with each other was also explored.

How Can the Professional Community Influence Teachers’ Work Engagement? The Mediating Role of Teacher Self-Efficacy

The sustainable development of education requires the continuous engagement of teachers, and the professional community has long been considered an important facilitator of teacher engagement. However, teachers’ professional community has often been analyzed as a unified construct, and thus the question of how teacher engagement is enhanced remains unanswered. Based on the conservation of resources theory, in this study, we investigated how teacher work engagement was affected by the crossover of job resources between the professional community (including shared norms, collective responsibility, collaboration, and reflective dialogue) and teachers (self-efficacy). The sample included 1123 primary and secondary school teachers in China. Covariance structural modeling was used to test our hypotheses. Shared norms and collective responsibility played a fundamental role and positively predicted collaboration, which in turn enhanced reflective dialogue. Teacher self-efficacy partially mediated the effect of the four dimensions of the professional community on teachers’ work engagement. The findings of this study indicate that the professional community offers valuable organizational and social resources that can be used by teachers to enhance their personal resources, such as self-efficacy, and thus become more engaged in their work. Shared norms and collective responsibility serve to shape a growth-oriented school culture that stimulates teachers’ willingness to collaborate and improves their confidence in teaching, and thus should be stressed by school leaders when introducing changes.

Relationships Among Pay-for-Performance, Work Stressors, and Depression in Sales Workers: A Structural Equation Model Analysis.

The aim of this study was to examine whether pay-for-performance (PFP) affects depression via work stressors. This study used data from self-administered questionnaires obtained from 1160 sales workers, and the data were analyzed using structural equation modeling (covariance structure analysis). Models included "long hour labor condition (LHLC)," which consisted of the number of working hours, hours worked per month, service overtime, and increase or decrease in working hours; seven work stressors; and the Center for Epidemiologic Studies Depression scale. According to the final model (CFI = 0.950, RMSEA = 0.035), PFP worsened LHLC (standardized total effect [STE] = 0.357) and improved job control (STE = 0.108), and although slightly, exacerbated depression via other work stressors (STE = 0.051). Our results suggest the need for measures to avoid prolonged overwork to prevent worsening of employee mental health when introducing or implementing PFP.

Mixed Multinomial Probit Model Accommodating Flexible Covariance Structure and Random Taste Variation: An Application to Commute Mode Choice Behavior

This paper developed a mixed multinomial probit (MMNP) model with alternative error specification and random coefficients (for both generic variables and personal attributes) to accommodate flexible covariance structure and taste variation. The MMNP model can be efficiently estimated with analytic approximations of multivariate normal cumulative distribution functions, which avoid defects of simulation-based integration in the mixed multinomial logit (MMNL) model. The integral dimension of the MMNL model increases as random coefficients increase, but it only depends on the number of available alternatives in the MMNP model. Simulation experiments and empirical analysis of Shanghai commuters’ mode choice behavior were undertaken to examine the performance of MMNP models. Both simulation results and empirical results show that MMNP models can well accommodate flexible covariance structures and taste variation reflected through random coefficients being associated with both generic and personal variables. Empirical results indicate that the MMNP model performs better than traditional discrete choice models, such as the multinomial logit, the cross-nested logit, MMNL, and multinomial probit models. Random coefficients of “in-vehicle time of car” and “number of companions” indicate taste heterogeneity and the identifiability of random coefficients associated with both generic and personal attributes. Pairwise positive correlations between car/taxi, bus/metro, and bus/bus and metro are to be expected. However, the positive correlation between the car and metro modes may be unique to the Chinese city, Shanghai, because of the developed metro system. Unequal error variances reflect heterogeneities in unspecified factors in commute modes’ utilities. The MMNP model will offer an alternative efficient way to accommodate taste heterogeneity and flexible error covariance structure in discrete choice models. Compared with the MMNL model, the MMNP model can accommodate more random coefficients without increasing computational complexity.

Selecting the covariance structure for the seemingly unrelated regression models

ObjectiveThis paper is concerned with evaluating suggested approach of selecting the suitable covariance structure for fitting the seemingly unrelated regression equations (SURE) models efficiently. MethodThe paper assessed AL-Marshadi (2014) methodology in terms of its percentage of times that it identifies the right covariance structure for mixed model analysis of SURE models using simulated data. ApplicationThe simulated equations of SURE models have identical explanatory variables, the regressors in one block of equations are a subset of those in another, and different regressors in the equations with various settings of covariance structures of ∑. Moreover, the percentage of times that REML fail to converge under normal situation are reported. The application of the proposed methodology is given using a panel of data. ConclusionsIn short, AL-Marshadi (2014) methodology provided an excellent tool for selecting the right covariance structure for SURE models using restricted maximum likelihood (REML) estimation method in order to fit the SURE models more efficiently than the existing method that considering the stander unstructured covariance structure in fitting SURE models.