Nonrecursive Structural Equation Models Research Articles

Applying the structural equation model approach to study the simultaneous relationship between women’s empowerment and mental disorder in Egypt

PurposeThe main purpose of this paper is to examine whether women’s empowerment and mental disorder affect each other in a one-way or two-way simultaneous relationship. Accordingly, the study fills a gap in the literature since it is the first attempt to examine the simultaneous relationship between women’s empowerment and mental disorder in Egypt. To achieve this, the study aims to examine the most important dimensions of women’s empowerment and mental disorder that affect each other simultaneously, and the most important determinants affecting women’s empowerment and mental disorder.Design/methodology/approachThe study depends on the cross-sectional data from the “Survey of Young People in Egypt” implemented in 2014. Married women aged 14–35 are included in the analysis (N = 3052). Recursive and nonrecursive structural equation models are used to examine the simultaneous relationship between women’s empowerment and mental disorder using AMOS, which stands for Analysis of Moment Structures (Version 22).ResultsWomen’s education has a positive significant impact on women’s empowerment and mental health. Violence has a positive significant impact on mental disorder, while it has a negative impact on women’s empowerment. Sexual harassment has a negative impact on treatment with spouse dimension. Regarding the one-way relationship, the results show that the more empowered the woman, the better her mental health is. Considering the two-way simultaneous relationship, the findings show that there is a partial two-way simultaneous relationship.ConclusionThere is a relationship between women’s empowerment and mental health, indicating that they affect each other simultaneously. Awareness of the importance of psychological counselling and treatment for mental disorders in women is needed.

Relationships between the residential environment, travel attitude and behaviour among knowledge workers: The role of job types

Given the ever-increasing auto dependence constituting a non-negligible portion of carbon emissions, unraveling the travel choice mechanism is crucial to designing effective sustainable urban policies. It is of great significance to investigate the impact of the residential built environment and travel attitude on travel behaviour. However, existing studies have not yet reached a consensus on the complex relationships between the built environment, travel attitude and travel behaviour. Thus, it is vital to further integrate other domains (e.g. job/employment) of an individual's life course to comprehensively understand individual travel behaviour.By integrating a novel perspective of knowledge typology (analytical, synthetic, and symbolic types of knowledge) in the job domain, this article further categorizes knowledge workers into three groups——scientific, engineering and creative workers. Based on the web survey data retrieved from 738 knowledge workers and 3924 other workers in Munich, both recursive and non-recursive structural equation models are applied to respectively estimate their travel choice mechanisms. Results show that “residential self-selection” applies more to creative workers, whereas “environmental determinism” applies more to engineering workers. The travel choice mechanism of scientific workers follows neither framework, with respect to no significant link between their residential environments and travel attitudes. In contrast, there coexist “environmental determinism” and “residential self-selection” among other workers.Regarding that the scientists, engineers and creatives potentially associate with heterogeneous travel choice rationales, future mobility studies in the era of knowledge economy should further integrate the job domain. Accordingly, “tailored-made” spatial and transport planning should be embedded in the local industrial structure and the variety of employment.

The impact of personal motivation on perceived effort and performance of pro-environmental behaviors.

In order to minimize climate change it is important that people take up a sustainable lifestyle. Sustainable lifestyles call for pro-environmental behaviors (PEBs) in several domains, such as in-home energy use, mobility, and consumption of food and goods. However, studies show that people often do not consistently behave pro-environmentally in all domains. In this study we investigated how a combination of personal motivation, and the difficulty and the perceived effort of a PEB, predicts the performance of PEBs in various domains, using a survey (n = 1,536). By means of Rasch analysis we identified the difficulty of 17 PEBs and estimated respondents’ pro-environmental motivations. In addition, we investigated if performance of certain PEBs increased the probability of performing other PEBs. This way we could identify for each level of motivation which behaviors respondents were (probably) performing and which behaviors they did not yet perform, but would be least effortful new behaviors. Furthermore, using a non-recursive structural equation model we investigated the relations between perceived effort, PEB performance, motivation, underlying traits, and demographics. Results showed a feedback loop between motivation and perceived effort: when respondents were motivated they perceived behaviors as less effortful and also lower perception of effort was related to higher motivation. Our results imply that people mainly perform PEBs that fit their level of pro-environmental motivation and that they are inclined to do the things of which they can justify the effort they need to invest. This amount of effort seems quite similar for people: no one wants to invest too much effort, but people highly differ in how effortful they assess different behaviors. Our study thus indicates that rationalizations play a key role. Encouraging people to embrace more sustainable lifestyles may involve step-by-step increases in PEB performance. We propose that people should be encouraged to perform behaviors that are closest to their current motivation level in order for them to progress from performing easy to more difficult PEBs.

Intergenerational Replication of Teenage Pregnancy and Educational Attainment in Mexico.

Mexico ranks among the OECD countries with the highest prevalence of teenage pregnancies, exhibiting a fertility rate of 70.6 births for every 1000 adolescents. Mexican adolescents with a history of pregnancy are twice as likely to lag behind in their studies as those who have not been pregnant. Research on adolescent maternity and its explanatory mechanisms is required as a basis for implementing policies and programs that effectively curb teenage pregnancy-related behaviors, prevent educational gaps, and reduce the intergenerational transmission of poverty. Based on quasi-experimental methodology and a non-recursive structural equation model with instrumental variables, this paper analyzed the intergenerational transmission of teenage pregnancy from mothers to daughters, as well as the relationship between teenage pregnancy and educational attainment. Using data from the 2009 National Survey of Demographic Dynamics in Mexico, our estimated model indicated a unidirectional relationship from teenage pregnancy to educational attainment. An association was observed between teenage pregnancy and an increased probability of a moderate or severe educational gap (≥ 1year) by 21% ± 5 and a severe educational gap (≥ 2years) by 33% ± 8. Adolescents whose mothers reported teenage pregnancy at < 15years of age were approximately 84% more likely to experience teenage pregnancy themselves than other adolescents. Relevant explanatory mechanisms included low socioeconomic status and a low level of education in the household. Mexico needs to formulate, implement, and expand comprehensive and early prevention strategies as well as teenage pregnancy care throughout its most vulnerable regions. Efforts should be made at the individual, family, and community levels; incorporate alliances with teenage networks; actively engage parents, teachers, and health care providers; and reinforce educational initiatives on sexual and reproductive health for adolescents. It would be convenient for the Government to implement public policies that emphasize the results obtained. There is no better instrument than to show the evidence of the gradual deterioration of human capital in Mexico associated with adolescent pregnancy.

The effect of aviation responses to the control of imported COVID-19 cases

The outbreak of the COVID-19 pandemic has a lasting and unprecedented negative impact on the global aviation industry. While countries such as China have successfully curbed the domestic outbreak of the virus with various restrictive and preventive measures, the challenge of avoiding imported cases remains. More importantly, it is still unclear to what extent these implemented aviation emergency responses have effectively mitigated the transmission risk of the virus. This paper provides an empirical assessment of aviation responses to the control of imported COVID-19 cases, with a focus on the following three strategies: the “circuit breaker” policy, the “negative Nucleic Acid testing (NAT)”, and the “double negative tests” requirement. Non-recursive structural equation models (SEM) with latent variables were applied to detailed international flight data and individual epidemic survey data of Guangzhou, China, between May 1 and November 30, 2020. The results show that the “double negative tests” measure has a positive effect on eliminating the number of SARS-CoV-2 carriers, while the effects of single “circuit breaker” and its co-intervention with “negative NAT” are conterproductive. This study provides important implications to civil aviation agencies in regard to medium and long-term risk control of imported cases. Specifically, although the circuit breaker mechanism was designed to target on the risk control of imported COVID-19 cases, it may be more effective to carefully maintain a timely and reliable pre-boarding screening and testing to curb the number of imported cases.

Trophic interactions among vertebrate guilds and plants shape global patterns in species diversity.

Trophic interactions play critical roles in structuring biotic communities. Understanding variation in trophic interactions among systems provides important insights into biodiversity maintenance and conservation. However, the relative importance of bottom-up versus top-down trophic processes for broad-scale patterns in biodiversity is poorly understood. Here, we used global datasets on species richness of vascular plants, mammals and breeding birds to evaluate the role of trophic interactions in shaping large-scale diversity patterns. Specifically, we used non-recursive structural equation models to test for top-down and bottom-up forcing of global species diversity patterns among plants and trophic guilds of mammals and birds (carnivores, invertivores and herbivores), while accounting for extrinsic environmental drivers. The results show that trophic linkages emerged as being more important to explaining species richness than extrinsic environmental drivers. In particular, there were strong, positive top-down interactions between mammal herbivores and plants, and moderate to strong bottom-up and/or top-down interactions between herbivores/invertivores and carnivores. Estimated trophic interactions for separate biogeographical regions were consistent with global patterns. Our findings demonstrate that, after accounting for environmental drivers, large-scale species richness patterns in plant and vertebrate taxa consistently support trophic interactions playing a major role in shaping global patterns in biodiversity. Furthermore, these results suggest that top-down forces often play strong complementary roles relative to bottom-up drivers in structuring biodiversity patterns across trophic levels. These findings underscore the importance of integrating trophic forcing mechanisms into studies of biodiversity patterns.

Identifiability of nonrecursive structural equation models

An approach to studying reciprocal-effects in a cross-sectional data is to apply nonrecursive structural equation models. This article takes a theoretical approach to study the identifiability problem of reciprocal-effect models. Identifiability conditions are presented under a variety of settings.

Environmental Filtering and Positive Plant Litter Feedback Simultaneously Explain Correlations Between Leaf Traits and Soil Fertility

Plant traits covary with soil fertility, but determining whether this is the outcome of environmental filtering or plant feedback is not straightforward, especially in long-lived plant communities such as rain forests. Without explicitly accounting for the potential of plant litter to influence soil properties, it is difficult to interpret with confidence that covariation between soil nutrients and plant traits is the outcome of environmental filtering. We estimated abundance-weighted mean leaf dry matter content (LDMC), senesced leaf litter nitrogen resorption proficiency (litter N %), wood tissue density, and multiple metrics of soil fertility (pH, C:N ratio, and organic P concentrations) on 241 temperate rain forest plots throughout New Zealand. A non-recursive structural equation model indicated that environmental filtering and plant litter feedback were equally important reciprocal processes that explain covariation between leaf traits and soil fertility. Plant communities with high resorption proficiency, high LDMC, and high stem tissue density were strongly associated with low-fertility soils. Both structural (LDMC) and chemical (litter N %) leaf traits influenced soil fertility, but stem tissue density did not exhibit feedback effects. Here, we show that it is not a matter of ‘either–or’ when determining the relative importance of environmental filtering and plant feedback, but rather that both processes are equally important and occur simultaneously in temperate forest ecosystems. Although both leaf and wood traits were filtered by soil fertility, only leaf traits exhibited significant feedback effects on soil fertility.

Modeling of Nonrecursive Structural Equation Models With Categorical Indicators

Nonrecursive structural equation models generally take the form of feedback loops, involving 2 latent variables that are connected by 2 unidirectional paths, 1 starting with each variable and terminating in the other variable. Nonrecursive models belong to a larger class of path models that require the use of instrumental variables (IVs) to achieve model identification. Prior research has focused on SEM parameter estimation with IVs when indicators were continuous and normally distributed. Much less is known about how estimators function in the presence of categorical indicators, which are commonly used in the social sciences, such as with cognitive and affective instruments. In this study, there was specific interest in comparing the 2-stage least squares (2SLS) estimator and its categorical variant to other recommended estimators. This study compares the performance of several estimation approaches for fitting structural equation models with categorical indicator variables when IVs are necessary to obtain proper model estimates. Across conditions, 1 extension of the nonlinear 2SLS (N2SLS) approach, the nonlinear 3-stage least squares (N3SLS), which accounts for correlated errors among regressors within each model (as does the N2SLS), as well as correlations of errors across models, which N2SLS does not, appears to work the best among methods compared.

Variable links within perceived police legitimacy?: Fairness and effectiveness across races and places

This work examines connections between two threads of community residents’ perceptions of local police legitimacy, effectiveness and procedural fairness, and how those links depend on race, place, and race/place combinations. Previous works have connected these two threads, but have failed (a) to explore the variability of that connection by race, place, and race/place combinations across communities spanning the urban to suburban to rural continuum or (b) to model mutual influence. An extension of the group position thesis and work on minority views of police practices suggest how these variations might be patterned. Data were derived from a 2003 probability-based sampling survey of household respondents across Pennsylvania (n=1289). Generalized confirmatory factor analysis models built procedural fairness and effectiveness indices for four groups: whites in urban core counties, non-whites in urban core counties, whites in non-urban core counties, and non-whites in non-urban core counties. Non-recursive structural equation models revealed variable impacts of perceived police effectiveness on perceived police fairness and, to a lesser extent, of fairness on effectiveness. Implications for a more structurally and contextually aware understanding of links in police legitimacy models are developed.

The store-as-a-brand strategy: The effect of store environment on customer responses

Despite their significance within the apparel industry, retailers selling just their own brand of apparel (single-brand apparel retailers) have not been examined for the relationship between their store environment and customer responses. This study explores the effect of store environment on customers’ internal evaluations and behavior toward single-brand apparel retailers. Further, to understand the store-as-a-brand strategy, this study examined whether customers have similar cognitive and affective perceptions toward the store versus merchandise. A mall intercept survey was conducted and a non-recursive structural equation model was employed to test the proposed hypotheses. This study found that social, design, and ambient cues as well as merchandise cues influence internal evaluations and ultimately approach behavior toward single-brand apparel retailers. This study also affirmed that the store-as-a-brand concept is valid for a single-brand apparel retailer.

Exploring the relationships between innovation and internationalization of small and medium‐sized enterprises: A nonrecursive structural equation model

AbstractThis article seeks to provide more insights on the two‐way link between internationalization and innovation by considering total, direct, and reciprocal effects using a nonrecursive structural model. Innovation is defined through product and process development, while internationalization is defined through inward and outward internationalization in both closer and farther markets. The results suggest that these two major sources of growth are linked by different sets of relations, from the investment in product and process innovation to outward internationalization in a closer market, or from inward and outward internationalization in farther markets to the investment in product innovation. Copyright © 2013 ASAC. Published by John Wiley &amp; Sons, Ltd.

Read anything mean lately? Associations between reading aggression in books and aggressive behavior in adolescents

Although there have been hundreds of studies on media violence, few have focused on literature, with none examining novels. Accordingly, the aim of the current study was to examine whether reading physical and relational aggression in books was associated with aggressive behavior in adolescents. Participants consisted of 223 adolescents who completed a variety of measures detailing their media use and aggressive behavior. A non-recursive structural equation model revealed that reading aggression in books was positively associated with aggressive behavior, even after controlling for exposure to aggression in other forms of media. Associations were only found for congruent forms of aggression. Implications regarding books as a form of media are discussed.

Seagrass–Sediment Feedback: An Exploration Using a Non-recursive Structural Equation Model

The reciprocal effects between sediment texture and seagrass density are assumed to play an important role in the dynamics and stability of intertidal–coastal ecosystems. However, this feedback relationship has been difficult to study empirically on an ecosystem scale, so that knowledge is mainly based on theoretical models and small-scale (experimental) studies. In this paper we apply a non-recursive structural equation model (SEM) to empirically investigate, at large spatial scale, the mutual dependence between seagrass (Zostera noltii) density and sediment texture, on the pristine, seagrass-dominated, intertidal mudflats of the Banc d’Arguin, Mauritania. The non-recursive SEM allows consistent estimation and testing of a direct feedback between sediment and seagrass whilst statistically controlling for the effects of nutrients and abiotic stress. The resulting model is consistent with the hypothesized negative feedback: grain size decreases with seagrass density, whereas fine grain size has a negative impact on seagrass density because it decreases pore water exchange which leads to hypoxic sediment conditions. Another finding is that seagrass density increases with sediment organic material content up to a threshold level beyond which it levels off. In combination with decreasing grain size, accumulation of organic matter creates hypoxic sediment conditions which lead to the production of toxic hydrogen sulfide which slows down seagrass growth. The negative feedback loop implies that intertidal Z. noltii modifies its own environment, thus controlling its growing conditions. To the best of our knowledge, this study is the first to demonstrate a direct negative feedback relationship in ecosystems by means of a non-recursive SEM.

Optimizing a control plan using a structural equation model with an application to statistical process analysis

In the case where non-experimental data are available from an industrial process and a directed graph for how various factors affect a response variable is known based on a substantive understanding of the process, we consider a problem in which a control plan involving multiple treatment variables is conducted in order to bring a response variable close to a target value with variation reduction. Using statistical causal analysis with linear (recursive and non-recursive) structural equation models, we configure an optimal control plan involving multiple treatment variables through causal parameters. Based on the formulation, we clarify the causal mechanism for how the variance of a response variable changes when the control plan is conducted. The results enable us to evaluate the effect of a control plan on the variance of a response variable from non-experimental data and provide a new application of linear structural equation models to engineering science.

Institutional Quality and Generalized Trust: A Nonrecursive Causal Model

This paper investigates the association between institutional quality and generalized trust. Despite the importance of the topic, little quantitative empirical evidence exists to support either unidirectional or bidirectional causality for the reason that cross-sectional studies rarely model the reciprocal relationship between institutional quality and generalized trust. Using data from the World Values Survey, World Bank, and other data sources in an identified nonrecursive structural equation model, results show that generalized trust and institutional quality form a positive reciprocal relationship, where the connection is stronger from generalized trust to institutional quality. The conclusion discusses implications for theory and policy in this area.

Blocked-Error-R 2: A Conceptually Improved Definition of the Proportion of Explained Variance in Models Containing Loops or Correlated Residuals

Bentler and Raykov (2000, Journal of Applied Psychology 85: 125–131), and Joreskog (1999a, http://www.ssicentral.com/lisrel/column3.htm, 1999b http://www.ssicentral. com/lisrel/column5.htm) proposed procedures for calculating R2 for dependent variables involved in loops or possessing correlated errors. This article demonstrates that Bentler and Raykov’s procedure can not be routinely interpreted as a “proportion” of explained variance, while Joreskog’s reduced-form calculation is unnecessarily restrictive. The new blocked-error-R2 (beR2) uses a minimal hypothetical causal intervention to resolve the variance-partitioning ambiguities created by loops and correlated errors. Hayduk (1996) discussed how stabilising feedback models – models capable of counteracting external perturbations – can result in an acceptable error variance which exceeds the variance of the dependent variable to which that error is attached. For variables included within loops, whether stabilising or not, beR2 provides the same value as Hayduk’s (1996) loop-adjusted-R2. For variables not involved in loops and not displaying correlated residuals, beR2 reports the same value as the traditional regression R2. Thus, beR2 provides a conceptualisation of the proportion of explained variance that spans both recursive and nonrecursive structural equation models. A procedure for calculating beR2 in any SEM program is provided.

Social Capital in Rural and Urban Communities: Testing Differences in Media Effects and Models

This study examines whether the effects of the mass media on social capital and related processes vary between rural and urban communities. A distinction is made between indicators of social networks (association membership and neighborliness), social trust (interpersonal trust and community trust), and pro-social behaviors (voting and volunteering). We test nonrecursive structural equation models with manifest and latent variables on rural and urban U.S. samples. Media effects differ by medium and by community type. Newspaper use has positive effects in each model, while those of entertainment TV viewing are negative. Local TV news use has positive effects in only the urban model, while network TV news use has positive effects in only the rural model. In addition, there is a reciprocal relationship between social networks and social trust in the rural model, while the relationship is linear—from social networks to social trust—in the urban model.

A Hierarchical Bayesian Methodology for Treating Heterogeneity in Structural Equation Models

Structural equation models are widely used in marketing and psychometric literature to model relationships between unobserved constructs and manifest variables and to control for measurement error. Most applications of structural equation models assume that data come from a homogeneous population. This assumption may be unrealistic, as individuals are likely to be heterogeneous in their perceptions and evaluations of unobserved constructs. In addition, individuals may exhibitdifferent measurement reliabilities. It is well-known in statistical literature that failure to account for unobserved sources of individual differences can resultin misleading inferences and incorrect conclusions. We develop a hierarchical Bayesian framework for modeling general forms of heterogeneity in partially recursive structural equation models. Our framework elucidates the motivations for accommodating heterogeneity and illustrates theoretically the types of misleading inferences that can result when unobserved heterogeneity is ignored. We describe in detail the choices that researchers can make in incorporating different forms of measurement and structural heterogeneity. Current random-coefficient models in psychometric literature can accommodate heterogeneity solely in mean structures. We extend these models by allowing for heterogeneity both in mean and covariance structures. Specifically, in addition to heterogeneity in measurement intercepts and factor means, we account for heterogeneity in factor covariance structure, measurement error, and structural parameters. Models such as random-coefficient factor analysis, random-coefficientsecond-order factor analysis, and random-coefficient, partially recursive simultaneous equation models are special cases of our proposed framework. We also develop Markov Chain Monte Carlo (MCMC) procedures to perform Bayesian inference in partially recursive, random-coefficient structural equation models. These procedures provide individual-specific estimates of the factor scores, structural coefficients, and other model parameters. We illustrate our approach using two applications. The first application illustrates our methods on synthetic data, whereas the second application uses consumer satisfaction data involving measurements on satisfaction, expectation disconfirmation, and performance variables obtained from a panel of subjects. Our results from the synthetic data application show that our Bayesian procedures perform well in recovering the true parameters. More importantly, we find that models that ignore heterogeneity can yield a severely distorted picture of the nature of associations among variables and can therefore generate misleading inferences. Specifically, we find that ignoring heterogeneity can result in inflated estimates of measurement reliability, wrong signs of factor covariances, and can yield attenuated model fit and standard errors. The results from the consumer satisfaction study show that individuals vary both in means and covariances and indicate that conventional psychometric methods are not appropriate for our data. In addition, we find that heterogeneous models outperform the standard structural equation model in predictive ability. Managerially, we show how one can use the individual-level factor scores and structural parameter estimates from the Bayesian approach to perform quadrantanalysis and refine marketing policy (e.g., develop a one-on-one marketing policy). The framework introduced in this paper and the inference procedures we describe should be of interest to researchers in a wide range of disciplines in which measurement error and unobserved heterogeneity are problematic. In particular, our approach is suitable for studies in which panel data or multiple observations are available for a given set of respondents or objects (e.g., firms, organizations, markets). At a practical level, our procedures can be used by managers and other policymakers to customize marketing activities or policies. Future research should extend our procedures to deal with the general nonrecursive structural equation model and to handle binary and ordinal data situations.

"On measures of explained variance in nonrecursive structural equation models": Correction.

"On measures of explained variance in nonrecursive structural equation models": Correction.