Comparing multiple statistical software for multiple-indicator, multiple-cause modeling: an application of gender disparity in adult cognitive functioning using MIDUS II dataset

Abstract Background The multiple-indicator, multiple-cause model (MIMIC) incorporates covariates of interest in the factor analysis. It is a special case of structural equation modeling (SEM), which is modeled under latent variable framework. The MIMIC model provides rigorous results and becomes broadly available in multiple statistical software. The current study introduces the MIMIC model and how it can be implemented using statistical software packages SAS CALIS procedure, R lavaan package, and Mplus version 8.0. Methods In this paper, we first discussed the formulation of the MIMIC model with regard to model specification and identification. We then demonstrated the empirical application of the MIMIC model with the Midlife in the United States II (MIDUS II) Study (N = 4109) using SAS CALIS procedure, R lavaan package and Mplus version 8.0 to examine gender disparities in cognitive functioning. The input, output, and diagram syntaxes of the three statistical software packages were also presented. Results In terms of data structure, all three statistical programs can be conducted using both raw data and empirical covariance matrix. SAS and R are comprehensive statistical analytic packages and encompass numerous data manipulation capacities. Mplus is designed primarily for latent variable modeling and has far more modeling flexibility compared to SAS and R, but limited in data manipulation. Differences in model results from the three statistical programs are trivial. Overall, the results show that while men show better performance in executive function than women, women demonstrate better episodic memory than men. Conclusions Our study demonstrates the utility of the MIMIC model in its empirical application, fitted with three popular statistical software packages. Results from our models align with empirical findings from previous research. We provide coding procedures and examples with detailed explanations in the hopes of providing a concise tutorial for researchers and methodologists interested in incorporating latent constructs with multiple indicators and multiple covariates in their research projects. Future researchers are encouraged to adopt this flexible and rigorous modeling approach.

Download Full-text

Comparing Multiple Statistical Software for Multiple-Indicator, Multiple-Cause Modeling: An Application of Gender Disparity in Adult Cognitive Functioning Using MIDUS II Dataset

10.21203/rs.2.20252/v4 ◽

2020 ◽

Author(s):

Chi Chang ◽

Joseph Gardiner ◽

Richard T Houang ◽

Yan-Liang Yu

Keyword(s):

Cognitive Functioning ◽

Latent Variable ◽

The United States ◽

Equation Modeling ◽

Statistical Software ◽

Mimic Model ◽

Empirical Application ◽

Data Manipulation ◽

Software Packages ◽

Multiple Indicator

Abstract Background The Multiple-indicator, multiple-cause model (MIMIC) incorporates covariates of interest in the factor analysis is a special case of structural equation modeling (SEM), which is modeled under latent variable framework. The MIMIC model provides rigorous results and becomes broadly available in multiple statistical software. The current study introduces the MIMIC model and how it can be implemented using statistical software packages SAS CALIS procedure, R lavaan package, and Mplus version 8.0. Methods In this paper, we first discussed the formulation of the MIMIC model with regard to model specification and identification. We then demonstrated the empirical application of the MIMIC model with the Midlife in the United States II (MIDUS II) Study (N=4,109) using SAS CALIS procedure, R lavaan package and Mplus version 8.0 to examine gender disparities in cognitive functioning. The input, output, and diagram syntaxes of the three statistical software packages were also presented.Results In terms of data structure, all three statistical programs can be conducted using both raw data and empirical covariance matrix. SAS and R are comprehensive statistical analytic packages and encompass numerous data manipulation capacities. Mplus is designed primarily for latent variable modeling and has far more modeling flexibility compared to SAS and R, but limited in data manipulation. Differences in model results from the three statistical programs are trivial. Overall, the results show that while men show better performance in executive function than women, women demonstrate better episodic memory than men.Conclusions Our study demonstrates the utility of the MIMIC model in its empirical application, fitted with three popular statistical software packages. Results from our models align with empirical findings from previous research. We provide coding procedures and examples with detailed explanations in the hopes of providing a concise tutorial for researchers and methodologists interested in incorporating latent constructs with multiple indicators and multiple covariates in their research projects. Future researchers are encouraged to adopt this flexible and rigorous modeling approach.

Download Full-text

Comparing Multiple Statistical Software for Multiple-Indicator, Multiple-Cause Modeling: An Application of Gender Disparity in Adult Cognitive Functioning Using MIDUS II Dataset

10.21203/rs.2.20252/v3 ◽

2020 ◽

Author(s):

Chi Chang ◽

Joseph Gardiner ◽

Richard T Houang ◽

Yan-Liang Yu

Keyword(s):

Cognitive Functioning ◽

Latent Variable ◽

The United States ◽

Gender Disparity ◽

Statistical Software ◽

Mimic Model ◽

Empirical Application ◽

Data Manipulation ◽

Software Packages ◽

Multiple Indicator

Abstract Background The Multiple-indicator, multiple-cause model (MIMIC) incorporates covariates of interest in the factor analysis using latent variable framework, of which classical structural equation model is a special case. The MIMIC model provides rigorous results and becomes broadly available in multiple statistical software. The current study introduces the MIMIC model and how it can be implemented using statistical software packages SAS CALIS procedure, R lavaan package, and Mplus version 8.0. Methods In this paper, we first discussed the formulation of the MIMIC model with regard to model specification and identification. We then demonstrated the empirical application of the MIMIC model with the Midlife in the United States II (MIDUS II) Study (N=4,109) using SAS CALIS procedure, R lavaan package and Mplus version 8.0 to examine gender disparities in cognitive functioning. The input, output, and diagram syntaxes of the three statistical software packages were also presented.Results In terms of data structure, all three statistical programs can be conducted using both raw data and empirical covariance matrix. SAS and R are comprehensive statistical analytic packages and encompass numerous data manipulation capacities. Mplus is designed primarily for latent variable modeling and has far more modeling flexibility compared to SAS and R, but limited in data manipulation. Differences in model results from the three statistical programs are trivial. Overall, the results show that while men show better performance in executive function than women, women demonstrate better episodic memory than men.Conclusions Our study demonstrates the utility of the MIMIC model in its empirical application, fitted with three popular statistical software packages. Results from our models align with empirical findings from previous research. We provide coding procedures and examples with detailed explanations in the hopes of providing a concise tutorial for researchers and methodologists interested in incorporating latent constructs with multiple indicators and multiple covariates in their research projects. Future researchers are encouraged to adopt this flexible and rigorous modeling approach.

Download Full-text

Comparing Multiple Statistical Software for Multiple-Indicator, Multiple-Cause Modeling: An Application of Gender Disparity in Adult Cognitive Functioning Using MIDUS II Dataset

10.21203/rs.2.20252/v1 ◽

2020 ◽

Author(s):

Chi Chang ◽

Joseph Gardiner ◽

Richard T Houang ◽

Yan-Liang Yu

Keyword(s):

Structural Equation Modeling ◽

Cognitive Functioning ◽

Structural Equation ◽

The United States ◽

Equation Modeling ◽

Statistical Software ◽

Mimic Model ◽

Empirical Application ◽

Data Manipulation ◽

Multiple Indicator

Abstract Background: The Multiple-indicator, multiple-cause model (MIMIC) incorporates covariates of interest in the factor analysis using structural equation modeling framework. The model provides rigorous results and becomes broadly available in multiple statistical software. The current study introduces the MIMIC model and how it can be implemented using statistical software SAS CALIS procedure, R lavaan package, and M plus version 8.0. Methods: In this paper, we first discussed the formulation of the MIMIC model with regard to model specification and identification. We then demonstrated the empirical application of the MIMIC model with the Midlife in the United States II (MIDUS II) Study (N=4,109) using SAS CALIS procedure, R lavaan package and M plus version 8.0 to examine gender disparities in cognitive functioning. The input, output, and diagram syntaxes of the three statistical software programs were also presented. Results In terms of data structure, all three statistical programs can be conducted using both raw data and empirical covariance matrix. While SAS and R are comprehensive statistical analytic packages and encompass numerous data manipulation capacities, M plus is designed primarily for structural equation modeling and therefore is limited in data manipulation. Differences in model results from the three statistical programs are trivial. Overall, the results show that while men show better performance in executive function than women, women demonstrate better episodic memory than men. Conclusions: Our study demonstrates the utility of the MIMIC model in its empirical application, fitted with three popular statistical software packages. Results from our models align with empirical findings from previous research. We provide coding procedures and examples with detailed explanations in the hopes of providing a concise tutorial for researchers and methodologists interested in incorporating latent constructs with multiple indicators and multiple covariates in their research projects. Future researchers are encouraged to adopt this flexible and rigorous modeling approach.

Download Full-text

Comparing Multiple Statistical Software for Multiple-Indicator, Multiple-Cause Modeling: An Application of Gender Disparity in Adult Cognitive Functioning Using MIDUS II Dataset

10.21203/rs.2.20252/v2 ◽

2020 ◽

Author(s):

Chi Chang ◽

Joseph Gardiner ◽

Richard T Houang ◽

Yan-Liang Yu

Keyword(s):

Cognitive Functioning ◽

Latent Variable ◽

The United States ◽

Gender Disparity ◽

Model Specification ◽

Statistical Software ◽

Mimic Model ◽

Empirical Application ◽

Data Manipulation ◽

Multiple Indicator

Abstract Background The Multiple-indicator, multiple-cause model (MIMIC) incorporates covariates of interest in the factor analysis using latent variable framework, of which classical structural equation model is a special case. The MIMIC model provides rigorous results and becomes broadly available in multiple statistical software. The current study introduces the MIMIC model and how it can be implemented using statistical software SAS CALIS procedure, R lavaan package, and Mplus version 8.0. Methods In this paper, we first discussed the formulation of the MIMIC model with regard to model specification and identification. We then demonstrated the empirical application of the MIMIC model with the Midlife in the United States II (MIDUS II) Study (N=4,109) using SAS CALIS procedure, R lavaan package and Mplus version 8.0 to examine gender disparities in cognitive functioning. The input, output, and diagram syntaxes of the three statistical software programs were also presented.Results In terms of data structure, all three statistical programs can be conducted using both raw data and empirical covariance matrix. SAS and R are comprehensive statistical analytic packages and encompass numerous data manipulation capacities. Mplus is designed primarily for latent variable modeling and has far more modeling flexibility compared to SAS and R, but limited in data manipulation. Differences in model results from the three statistical programs are trivial. Overall, the results show that while men show better performance in executive function than women, women demonstrate better episodic memory than men.Conclusions Our study demonstrates the utility of the MIMIC model in its empirical application, fitted with three popular statistical software packages. Results from our models align with empirical findings from previous research. We provide coding procedures and examples with detailed explanations in the hopes of providing a concise tutorial for researchers and methodologists interested in incorporating latent constructs with multiple indicators and multiple covariates in their research projects. Future researchers are encouraged to adopt this flexible and rigorous modeling approach.

Download Full-text

ADHD: Restricted Phenotypes Prevalence, Comorbidity, and Polygenic Risk Sensitivity in ABCD Baseline Cohort

10.31234/osf.io/uxbh3 ◽

2021 ◽

Author(s):

Michaela Maria Cordova ◽

Dylan Matthew Antovich ◽

Peter Ryabinin ◽

Christopher Neighbor ◽

Michael A. Mooney ◽

...

Keyword(s):

Cognitive Functioning ◽

Latent Variables ◽

Latent Variable ◽

Present Report ◽

Sampling Bias ◽

The United States ◽

Operational Definition ◽

Polygenic Risk ◽

Phenotype Definition ◽

Composite Scores

Introduction. Estimates of prevalence and comorbidity of ADHD in the United States require additional national, multi-informant data. Further, it is unclear whether the polygenic, neurodevelopmental model of ADHD in DSM-5 is best modeled with a broad or restrictive phenotype definition. Method: In the Adolescent Behavior Cognition Development (ABCD) study baseline data on 9-10 year old children, ADHD prevalence, comorbidity, and association with cognitive functioning and polygenic risk were calculated at four thresholds of definition of ADHD phenotype restrictiveness using multiple measures and informants. Multi-indicator latent variable and composite scores were created and cross validated for ADHD symptoms and for irritability. Missing data, sample nesting, and sampling bias were corrected statistically. Results: Multi-informant estimate of ADHD prevalence by the most restrictive definition was 3.53% when restricted to children in which parent ratings and teacher ratings both converged with KSAD report of current ADHD. As stringency of the phenotype was increased, total comorbidity increased slightly, and associations with cognitive functioning and polygenic risk strengthened. Inclusion of children with past ADHD but now treated increased prevalence estimate without weakening detection of polygenic risk. Irritability and ADHD dimensional composite scores and latent variables achieved satisfactory model fit and expected external correlations. Conclusion: The present report strengthens estimates of ADHD prevalence and comorbidity. Research on polygenic and other correlates of ADHD as a clinical category in the ABCD sample may benefit from using a restrictive, multi-informant operational definition.

Download Full-text

Neuroimaging of Individual Differences: A Latent Variable Modeling Perspective

10.31234/osf.io/jryfm ◽

2018 ◽

Author(s):

Shelly Renee Cooper ◽

Joshua James Jackson ◽

Deanna Barch ◽

Todd Samuel Braver

Keyword(s):

Individual Differences ◽

Individual Difference ◽

Latent Variable ◽

Structural Equation ◽

Behavioral Measure ◽

Equation Modeling ◽

Latent Variable Modeling ◽

Psychometric Theory ◽

Human Connectome Project ◽

Neuroimaging Data

Neuroimaging data is being increasingly utilized to address questions of individual difference. When examined with task-related fMRI (t-fMRI), individual differences are typically investigated via correlations between the BOLD activation signal at every voxel and a particular behavioral measure. This can be problematic because: 1) correlational designs require evaluation of t-fMRI psychometric properties, yet these are not well understood; and 2) bivariate correlations are severely limited in modeling the complexities of brain-behavior relationships. Analytic tools from psychometric theory such as latent variable modeling (e.g., structural equation modeling) can help simultaneously address both concerns. This review explores the advantages gained from integrating psychometric theory and methods with cognitive neuroscience for the assessment and interpretation of individual differences. The first section provides background on classic and modern psychometric theories and analytics. The second section details current approaches to t-fMRI individual difference analyses and their psychometric limitations. The last section uses data from the Human Connectome Project to provide illustrative examples of how t-fMRI individual differences research can benefit by utilizing latent variable models.

Download Full-text

Resilience in Adolescence: Prospective Self Moderates the Association of Early Life Adversity with Psychopathology

10.31234/osf.io/g2yb9 ◽

2019 ◽

Author(s):

Mary Elizabeth Zinn ◽

Edward Huntley ◽

Daniel Keating

Keyword(s):

Behavior Problems ◽

Identity Formation ◽

Externalizing Behavior ◽

Early Life ◽

The United States ◽

Externalizing Behavior Problems ◽

Developmental Period ◽

Equation Modeling ◽

Early Life Adversity ◽

Latent Construct

Introduction. Early life adversity (ELA) can result in negative health-outcomes, including psychopathology. Evidence suggests that adolescence is a critical developmental period for processing ELA. Identity formation, which is crucial to this developmental period, may moderate the effect between ELA and psychopathology. One potential moderating variable associated with identity formation is Prospective Self, a latent construct comprised of future-oriented attitudes and behaviors.Methods. Participants are from the first wave of an ongoing longitudinal study designed to characterize behavioral and cognitive correlates of risk behavior trajectories. A community sample of 10th and 12th grade adolescents (N = 2017, 55% female) were recruited from nine public school districts across eight Southeastern Michigan counties in the United States. Data were collected in schools during school hours or after school via self-report, computer-administered surveys. Structural equation modeling was used in the present study to assess Prospective Self as a latent construct and to evaluate the relationship between ELA, psychopathology, and Prospective Self.Results. Preliminary findings indicated a satisfactory fit for the construct Prospective Self. The predicted negative associations between Prospective Self and psychopathology were found and evidence of moderation was observed for externalizing behavior problems, such that the effects of ELA were lower for individuals with higher levels of Prospective Self. Conclusion. These results support the role of Prospective Self in conferring resilience against externalizing behavior problems associated with ELA among adolescents. Keywords: Adolescence, Adverse Childhood Experiences, Psychopathology, Self-concept, Adolescent Health, Early Life Adversity

Download Full-text

Postpartum depression symptoms in survey-based research: a structural equation analysis

BMC Public Health ◽

10.1186/s12889-020-09999-2 ◽

2021 ◽

Vol 21 (1) ◽

Author(s):

Che Wan Jasimah Bt Wan Mohamed Radzi ◽

Hashem Salarzadeh Jenatabadi ◽

Nadia Samsudin

Keyword(s):

Postpartum Depression ◽

Latent Variable ◽

Structural Equation ◽

Depression Scale ◽

Public Health Problem ◽

Equation Modeling ◽

Depression Symptoms ◽

Postpartum Women ◽

Unhealthy Food ◽

High Level

Abstract Background Since the last decade, postpartum depression (PPD) has been recognized as a significant public health problem, and several factors have been linked to PPD. Mothers at risk are rarely undetected and underdiagnosed. Our study aims to determine the factors leading to symptoms of depression using Structural Equation Modeling (SEM) analysis. In this research, we introduced a new framework for postpartum depression modeling for women. Methods We structured the model of this research to take into consideration the Malaysian culture in particular. A total of 387 postpartum women have completed the questionnaire. The symptoms of postpartum depression were examined using the Edinburgh Postnatal Depression Scale (EPDS), and they act as a dependent variable in this research model. Results Four hundred fifty mothers were invited to participate in this research. 86% of the total distributed questionnaire received feedback. The majority of 79.6% of respondents were having depression symptoms. The highest coefficients of factor loading analysis obtained in every latent variable indicator were income (β = 0.77), screen time (β = 0.83), chips (β = 0.85), and anxiety (β = 0.88). Lifestyle, unhealthy food, and BMI variables were directly affected by the dependent variable. Based on the output, respondents with a high level of depression symptoms tended to consume more unhealthy food and had a high level of body mass indexes (BMI). The highest significant impact on depression level among postpartum women was unhealthy food consumption. Based on our model, the findings indicated that 76% of the variances stemmed from a variety of factors: socio-demographics, lifestyle, healthy food, unhealthy food, and BMI. The strength of the exogenous and endogenous variables in this research framework is strong. Conclusion The prevalence of postpartum women with depression symptoms in this study is considerably high. It is, therefore, imperative that postpartum women seek medical help to prevent postpartum depressive symptoms from worsening.

Download Full-text

Insights Into the Correspondence Between Land Use Pattern and Spatial Distribution of Rail Transit Services

Applied Spatial Analysis and Policy ◽

10.1007/s12061-021-09385-4 ◽

2021 ◽

Author(s):

Zhongqi Wang ◽

Qi Han ◽

Bauke de Vries ◽

Li Dai

Keyword(s):

Land Use ◽

Spatial Distribution ◽

Operations Management ◽

Latent Variable ◽

Structural Equation ◽

Equation Modeling ◽

Rail Transit ◽

Land Use Patterns ◽

Transit Services ◽

The Relationship

AbstractThe identification of the relationship between land use and transport lays the foundation for integrated land use and transport planning and management. This work aims to investigate how rail transit is linked to land use. The research on the relationship between land use and rail-based transport is dominated by the impacts of rail projects on land use, without an in-depth understanding of the reverse. However, it is important to note that issues of operation management rather than new constructions deserve greater attention for regions with established rail networks. Given that there is a correspondence between land use patterns and spatial distribution of heavy railway transit (HRT) services at such regions, the study area (i.e., the Netherlands) is partitioned by the Voronoi diagram of HRT stations and the causal relationship between land use and HRT services is examined by structural equation modeling (SEM). The case study of Helmond (a Dutch city) shows the potential of the SEM model for discussing the rail station selection problem in a multiple transit station region (MTSR). Furthermore, in this study, the node place model is adapted with the derivatives of the SEM model (i.e., the latent variable scores for rail service levels and land use characteristics), which are assigned as node and place indexes respectively, to analyze and differentiate the integration of land use and HRT services at the regional level. The answer to whether and how land use affects rail transit services from this study strengthens the scientific basis for rail transit operations management. The SEM model and the modified node place model are complementary to be used as analytical and decision-making tools for rail transit-oriented regional development.

Download Full-text

Correlated personality change across time and age

European Journal of Personality ◽

10.1177/08902070211014054 ◽

2021 ◽

pp. 089020702110140

Author(s):

Gabriel Olaru ◽

Mathias Allemand

Keyword(s):

Structural Equation ◽

Rank Order ◽

Personality Development ◽

The United States ◽

Change Score ◽

Personality Change ◽

Equation Modeling ◽

Model Parameters ◽

Cross Sectional ◽

Adult Lifespan

The goal of this study was to examine differential and correlated change in personality across the adult lifespan. Studying differential and correlated change can help understand whether intraindividual trait change trajectories deviate from the norm and how these trajectories are coupled with each other. We used data from two large longitudinal panel studies from the United States that covered a total age range of 20 to 95 years on the first measurement occasion. We used correlated factor models and bivariate latent change score models to examine the rank-order stability and correlations between change across three measurement waves covering 18 years ( N = 3250) and four measurement waves covering 12 years ( N = 4145). We examined the moderation effects of continuous age on these model parameters using local structural equation modeling. The results suggest that the test–retest correlations decrease with increasing time between measurements but are unaffected by participants’ age. We found that change processes in Extraversion, Openness, Agreeableness, and Conscientiousness were strongly related, particularly in late adulthood. Correlated change patterns were highly stable across time intervals and similar to the initial cross-sectional Big Five correlations. We discuss potential mechanisms and implications for personality development research.

Download Full-text