Subgroup Discovery in Structural Equation Model

Structural equation modeling (SEM) is one of the most popular statistical frameworks in the social and behavioural sciences. Often, detection of groups with distinct sets ofparameters in structural equation models (SEM) are of key importance for appliedresearchers, for example, when investigating differential item functioning for a mentalability test or examining children with exceptional educational trajectories. In this paper, we present a new approach combining subgroup discovery – a well-established toolkit of supervised learning algorithms and techniques from the field of computer science – with structural equation models. We provide an introduction how subgroup discovery can be applied to detect subgroups with exceptional parameter constellations in structural equation models based on user-defined interestingness measures. Furthermore, technical details on the algorithmic components, efficiency, and further computational aspects are presented. Then, our approach is illustrated with two real-world data examples, examining measurement invariance of a mental ability test and investigating interesting subgroups for the mediated relationship between predictors of educational outcomes and the trajectories of math competencies in 5th grade children. The illustrative examples are accompanied bya short introduction in the R package subgroupsem, which is a viable implementation of our approach for applied researchers.

Download Full-text

How to Test Replication for Structural Equation Models

10.31234/osf.io/uvh5s ◽

2019 ◽

Author(s):

Marielle Zondervan-Zwijnenburg

Keyword(s):

Structural Equation ◽

Structural Equation Models ◽

R Package ◽

Equation Model ◽

Latent Growth Curve ◽

P Value ◽

Growth Curve Model ◽

Latent Growth ◽

Latent Growth Curve Model ◽

Curve Model

This paper introduces the prior predictive p-value as a manner to test replication in structural equation models. Using the replication of a piecewise latent growth model as a running example, the study explains the steps of the prior predictive p-value and illustrates them with R-code. The R-code included in the paper and the Supplementary R-script guides the reader through each analysis step. All steps to compute the prior predictive p-value are also incorporated in the Replication R-package. Finally, the study demonstrates how the replication of a more advanced structural equation model - a multilevel latent growth curve model - can be tested.

Download Full-text

Structural Equation Modeling (SEM)-Based Meta-Analysis

10.31234/osf.io/93nfr ◽

2021 ◽

Author(s):

Mike W.-L. Cheung

Keyword(s):

Social Sciences ◽

Structural Equation Modeling ◽

Structural Equation ◽

Structural Equation Models ◽

Meta Analysis ◽

Equation Model ◽

Equation Modeling ◽

Future Directions ◽

Software Packages ◽

Meta Analyses

Structural equation modeling (SEM) and meta-analysis are two popular techniques in the behavioral, medical, and social sciences. They have their own research communities, terminologies, models, software packages, and even journals. This chapter introduces SEM-based meta-analysis, an approach to conduct meta-analyses using the SEM framework. By conceptualizing studies in a meta-analysis as subjects in a structural equation model, univariate, multivariate, and three-level meta-analyses can be fitted as structural equation models using definition variables. We will review fixed-, random-, and mixed-effects models using the SEM framework. Examples will be used to illustrate the procedures using the metaSEM and OpenMx packages in R. This chapter closes with a discussion of some future directions for research.

Download Full-text

R-squared of a Latent Interaction in Structural Equation Model: A Tutorial of Using R

International Journal of Statistics and Probability ◽

10.5539/ijsp.v10n3p69 ◽

2021 ◽

Vol 10 (3) ◽

pp. 69

Author(s):

Lu Qin ◽

Jihong Zhang ◽

Xinya Liang ◽

Qianqian Pan

Keyword(s):

Interaction Effect ◽

Structural Equation ◽

Social Science Research ◽

Science Research ◽

R Package ◽

Interaction Effects ◽

Equation Model ◽

Equation Modeling ◽

Main Effects ◽

Variance Explained

Mplus (Muthén & Muthén, 1998 - 2017) is one popular statistical software to estimate the latent interaction effects using the latent moderated structural equation approach (LMS). However, the variance explained by a latent interaction that supports the interpretation of estimation results is not currently available from the Mplus output. To relieve human computations and to facilitate interpretations of latent interaction effects in social science research, we developed two functions (LIR & LOIR) in the R package IRmplus to calculate the R-squared of a latent interaction above and beyond the first-order simple main effects in Structural Equation Modeling. This tutorial provides a step-by-step guide for applied researchers to estimating a latent interaction effect in Mplus, and to obtaining the R-squared of a latent interaction effect using the LIR & LOIR functions. Example data and syntax are available online.

Download Full-text

Forced Zero Cross-Loading Misspecifications in Measurement Component of Structural Equation Models

Methodology ◽

10.1027/1614-2241/a000084 ◽

2014 ◽

Vol 10 (4) ◽

pp. 138-152 ◽

Cited By ~ 5

Author(s):

Hsien-Yuan Hsu ◽

Susan Troncoso Skidmore ◽

Yan Li ◽

Bruce Thompson

Keyword(s):

Structural Equation ◽

Structural Model ◽

Structural Equation Models ◽

Equation Model ◽

Model Fit ◽

Model Specification ◽

Simulation Design ◽

Measurement Models ◽

Fit Statistics ◽

Path Coefficients

The purpose of the present paper was to evaluate the effect of constraining near-zero parameter cross-loadings to zero in the measurement component of a structural equation model. A Monte Carlo 3 × 5 × 2 simulation design was conducted (i.e., sample sizes of 200, 600, and 1,000; parameter cross-loadings of 0.07, 0.10, 0.13, 0.16, and 0.19 misspecified to be zero; and parameter path coefficients in the structural model of either 0.50 or 0.70). Results indicated that factor pattern coefficients and factor covariances were overestimated in measurement models when near-zero parameter cross-loadings constrained to zero were higher than 0.13 in the population. Moreover, the path coefficients between factors were misestimated when the near-zero parameter cross-loadings constrained to zero were noteworthy. Our results add to the literature detailing the importance of testing individual model specification decisions, and not simply evaluating omnibus model fit statistics.

Download Full-text

Evaluating the Observed Log-Likelihood Function in Two-Level Structural Equation Modeling with Missing Data: From Formulas to R Code

Psych ◽

10.3390/psych3020017 ◽

2021 ◽

Vol 3 (2) ◽

pp. 197-232

Author(s):

Yves Rosseel

Keyword(s):

Structural Equation ◽

Structural Equation Models ◽

Likelihood Function ◽

Likelihood Estimation ◽

Missing At Random ◽

Equation Modeling ◽

Computationally Efficient ◽

Log Likelihood ◽

Efficient Expression ◽

Special Case

This paper discusses maximum likelihood estimation for two-level structural equation models when data are missing at random at both levels. Building on existing literature, a computationally efficient expression is derived to evaluate the observed log-likelihood. Unlike previous work, the expression is valid for the special case where the model implied variance–covariance matrix at the between level is singular. Next, the log-likelihood function is translated to R code. A sequence of R scripts is presented, starting from a naive implementation and ending at the final implementation as found in the lavaan package. Along the way, various computational tips and tricks are given.

Download Full-text

Researchers’ awareness about plagiarism and impact of plagiarism detection tools – does awareness effect the actions towards preventing plagiarism?

Digital Library Perspectives ◽

10.1108/dlp-10-2020-0100 ◽

2021 ◽

Vol ahead-of-print (ahead-of-print) ◽

Author(s):

Sk. Mamun Mostofa ◽

Mashiat Tabassum ◽

S.M. Zabed Ahmed

Keyword(s):

Structural Equation ◽

Structural Model ◽

Personal Characteristics ◽

Equation Model ◽

Equation Modeling ◽

Plagiarism Detection ◽

Chi Square ◽

Content Type ◽

Reported Study ◽

Chi Square Test

Purpose This paper aims to analyse researchers’ awareness about plagiarism and impact of plagiarism detection tools on the actions that they take to prevent plagiarism. It also employs a structural model that examines whether awareness of plagiarism and anti-plagiarism tools have any significant effect on the actions taken by the researchers to avoid plagiarism. Design/methodology/approach A survey questionnaire was distributed to researchers at a large public university in Bangladesh. The survey accumulated 184 valid responses. Descriptive statistics were obtained to assess researchers’ awareness about plagiarism and impact of plagiarism detection tools and the actions taken by them. The reasons that may cause plagiarism were also identified. The awareness of the availability of the anti-plagiarism software that was being used by the university and its actual use by the researchers was gathered through the survey. Non-parametric Mann–Whitney and Kruskal–Wallis tests were conducted to investigate the differences in awareness levels and actions in terms of gender, age, discipline and current level of research. The chi-square test was carried out to examine the relationship between awareness about the availability of the anti-plagiarism software and its use by the researchers. Finally, the survey data were analysed using structural equation modeling to examine the effects of awareness of plagiarism and anti-plagiarism software on the actions taken by the researchers. Findings The study revealed that the level of awareness regarding plagiarism and impact of plagiarism detection software is generally high among the researchers. There are some significant differences between researchers’ demographic and personal characteristics and their awareness levels and actions with regard to plagiarism. The findings indicate that almost three-quarters of the researchers were aware about the anti-plagiarism tool that is being used, whereas more than half of the researchers indicated that they used the software to assess their works. The results of the structural equation model do not show a good fit, although there is strong statistical evidence that awareness about plagiarism and anti-plagiarism software has significantly impacted researchers’ actions towards preventing plagiarism. Originality/value There is no reported study on researchers’ awareness of plagiarism and its affiliated issues in Bangladesh. The findings of this study will not only provide useful insights regarding awareness about plagiarism but also assist university authorities to formulate relevant policy and take necessary actions against plagiarism in higher education institutions.

Download Full-text

Stepfamily Closeness and Depression Among American Indian Emerging Adults: A Structural Equation Modeling Approach

Journal of Family Issues ◽

10.1177/0192513x18808574 ◽

2018 ◽

Vol 40 (3) ◽

pp. 267-292 ◽

Cited By ~ 4

Author(s):

Kaitlin P. Ward ◽

Gordon E. Limb ◽

Sarah Higbee ◽

Helena Haueter

Keyword(s):

American Indian ◽

Emerging Adults ◽

American Indians ◽

Structural Equation ◽

The United States ◽

Equation Model ◽

Equation Modeling ◽

Racial Groups ◽

Biological Parent ◽

Parent Child

Stepfamilies are one of the fastest growing family structures among all racial groups in the United States. Stepfamily research among many racial groups, specifically American Indians, is virtually nonexistent. This is unfortunate, as American Indians are more likely to divorce and remarry compared with other populations. From a family systems perspective, this study examined whether retrospectively perceived closeness in three stepfamily relationships, namely child–residential biological parent, child–residential stepparent, and child–stepsibling, were negatively associated with depression scores in 226 American Indian emerging adults. A structural equation model showed that increased child–residential biological parent and child–stepsibling closeness predicted decreased depression scores, whereas child–residential stepparent closeness did not. We also found that depression scores significantly predicted retrospective perceptions of child–residential biological parent, child–residential stepparent, and child–stepsibling closeness. Findings encourage interventions that strengthen American Indian child–residential biological parent and child–stepsibling relationships, and underscore the need for further research that explores American Indian stepfamily relationships.

Download Full-text

Examining the ParticipACTION brand using the brand equity pyramid

Journal of Social Marketing ◽

10.1108/jsocm-11-2017-0071 ◽

2018 ◽

Vol 8 (4) ◽

pp. 378-396 ◽

Cited By ~ 3

Author(s):

Alexander Lithopoulos ◽

Peter A. Dacin ◽

Tanya R. Berry ◽

Guy Faulkner ◽

Norm O’Reilly ◽

...

Keyword(s):

Factor Analysis ◽

Confirmatory Factor Analysis ◽

Exploratory Factor Analysis ◽

Brand Equity ◽

Structural Equation ◽

Structural Equation Models ◽

Equation Modeling ◽

Content Type ◽

Activity Promotion ◽

Confirmatory Factor

Purpose The brand equity pyramid is a theory that explains how people develop loyalty and an attachment to a brand. The purpose of this study is to test whether the predictions made by the theory hold when applied to the brand of ParticipACTION, a Canadian non-profit organization that promotes active living. A secondary objective was to test whether this theory predicted intentions to be more physically active. Design/methodology/approach A research agency conducted a cross-sectional, online brand health survey on behalf of ParticipACTION. Exploratory factor analysis and confirmatory factor analysis established the factor structure. Structural equation modeling was used to test the hypothesized model. Findings A nationally representative sample of Canadian adults (N = 1,191) completed the survey. Exploratory factor analysis and confirmatory factor analysis supported a hypothesized five-factor brand equity framework (i.e. brand identity, brand meaning, brand responses, brand resonance and intentions). A series of structural equation models also provided support for the hypothesized relationships between the variables. Practical implications Though preliminary, the results provide a guide for understanding the branding process in the activity-promotion context. The constructs identified as being influential in this process can be targeted by activity-promotion organizations to improve brand strength. A strong organizational brand could augment activity-promotion interventions. A strong brand may also help the organization better compete against other brands promoting messages that are antithetical to their own. Originality/value This is the first study to test the brand equity pyramid using an activity-promotion brand. Results demonstrate that the brand equity pyramid may be useful in this context.

Download Full-text

Patient Engagement in Health Management as a Mediator Between Perceived Risk and COVID-19 Related Distress in Patients With IBD: A Structural Equation Model

Frontiers in Psychiatry ◽

10.3389/fpsyt.2021.733544 ◽

2021 ◽

Vol 12 ◽

Author(s):

Greta Castellini ◽

Lorenzo Palamenghi ◽

Mariarosaria Savarese ◽

Serena Barello ◽

Salvatore Leone ◽

...

Keyword(s):

Psychological Distress ◽

Perceived Stress ◽

Patient Engagement ◽

Perceived Risk ◽

Structural Equation ◽

Structural Equation Models ◽

Health Management ◽

Equation Model ◽

Online Questionnaire ◽

The Impact

Objective: This study aimed to evaluate the impact of the COVID-19 emergency on patients with IBD's psychological distress, understanding the role of patient engagement as a mediator.Methods: An online questionnaire was created, measuring perceived risk susceptibility toward COVID-19, perceived stress, and patient engagement. The questionnaire was distributed to a purposive sample of IBD patients who belonged to the Italian Association for patients with IBD (AMICI Onlus) in April 2020. Structural equation models were implemented.Results: The effect of the perceived risk susceptibility toward COVID-19 contagion on the perceived stress is fully mediated by patient engagement (β = 0.306, p < 0.001). Moreover, the patient engagement mitigates the perceived stress (β = −0.748, p < 0.001) in our sample of IBD patients, and it is negatively influenced by the perceived risk susceptibility toward COVID-19 (β = −0.410, p < 0.001).Conclusion: Patient engagement is the key factor that explains how the perceived risk susceptibility toward COVID-19 affects the perceived psychological distress in patients with IBD, underlining that the perceived risk of contagion increases their perceived level of stress through a decrease of patient engagement.

Download Full-text

Cyberchondria severity and quality of life among Lebanese adults: the mediating role of fear of COVID-19, depression, anxiety, stress and obsessive–compulsive behavior—a structural equation model approach

BMC Psychology ◽

10.1186/s40359-021-00674-8 ◽

2021 ◽

Vol 9 (1) ◽

Author(s):

Clara Rahme ◽

Marwan Akel ◽

Sahar Obeid ◽

Souheil Hallit

Keyword(s):

Quality Of Life ◽

Structural Equation ◽

Equation Model ◽

Mediating Effect ◽

Equation Modeling ◽

Obsessive Compulsive ◽

Online Questionnaire ◽

Cross Sectional ◽

Compulsive Disorder

Abstract Background This study highlights the significant association between cyberchondria and quality of life among the Lebanese population in the time of COVID-19. The aim was to assess the association between cyberchondria and quality of life (QOL) of Lebanese community during the COVID-19 pandemic and assess the mediating effect of fear of COVID-19, depression, anxiety, stress and Yale-Brown Obsessive–Compulsive Scale in this association. Methods This cross-sectional study was carried out between December 2020 and January 2021, during the COVID-19 pandemic. A total of 449 persons participated in this study by filling the online questionnaire. Structural equation modeling (SEM) was performed to examine the structural relationship between cyberchondria severity, the mediator (anxiety, stress, depression, obsessive–compulsive disorder (OCD) and fear of COVID-19) and physical/mental QOL. Results Having a university level of education and older age were significantly associated with higher physical QOL scores, whereas higher obsession-compulsion disorder, higher stress and higher anxiety were significantly associated with lower physical QOL scores. Higher anxiety was significantly associated with lower mental QOL scores. The results of the SEM showed that stress, fear of COVID-19 and to a lesser limit OCD, mediated the association between cyberchondria severity and physical QOL, whereas anxiety, stress and fear of COVID-19 mediated the association between cyberchondria severity and mental QOL. Conclusion This research reported interesting results encouraging more exploration of cyberchondria and its association with quality of life during this unique period of the pandemic. However, this virus has altered the lives of individuals all across the world, and the consequences will last for a long time. Along with all of the steps done to stop the development of COVID-19 and improve physical outcomes, mental health requires immediate care. More research is needed to determine the coping techniques people are employing to deal with the pandemic.

Download Full-text