Structural equation modeling with ordinal variables: a large sample case study

Şimşek, Gülhayat Gölbaşı; Noyan, Fatma

doi:10.1007/s11135-011-9467-4

Cited by 15 publications

(12 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…En cuanto al método de estimación utilizado en el presente estudio, ULS contribuye a que los resultados del índice RMSEA no estén distorsionados aunque el tamaño muestral sea elevado (Simsek y Noyan, 2012).…”

Section: Discussionunclassified

Análisis factorial confirmatorio. Recomendaciones sobre mínimos cuadrados no ponderados en función del error Tipo I de Ji-Cuadrado y RMSEA

et al. 2015

View full text Add to dashboard Cite

Resumen En Psicología, para obtener evidencias sobre validez de constructo mediante Análisis Factorial Confirmatorio es habitual trabajar con variables ordinales que presentan asimetría. En este estudio de simulación se analiza el comportamiento del método de Mínimos Cuadrados no Ponderados (ULS) en escalas tipo Likert con base en los índices χ2 de razón de verosimilitud (C2) y RMSEA. Para ello, se han manipulado cuatro factores experimentales: el número de factores o dimensiones (2, 3, 4, 5, 6), número de puntos de respuesta (3, 4, 5, 6), grado de asimetría de la distribución de respuestas (simétrica, asimétrica moderada y severa) y tamaño muestral (100, 150, 250, 450, 650, 850) de los modelos simulados. Según los principales resultados, el índice C2 muestra siempre un error Tipo I mayor que RMSEA, con independencia de los factores experimentales analizados. Finalmente, se discuten diferentes alternativas de acción y se presentan futuras líneas de investigación. AbstractIn order to obtain evidences about construct validity through Confirmatory Factor Analysis in Social Sciences, working with skewed ordinal variables has been usual. In this simulation study the performance of Unweighted Least Squares (ULS) method in Likert scales according to Likelihood Ratio Test (C2) and RMSEA indices is analysed through Type I error. For this purpose, four experimental factors have been manipulated: the number of factors or dimensions (2, 3, 4, 5, 6), the number of response points (3, 4, 5, 6), the degree of skewness of the responses distribution (symmetric, moderately and severely asymmetric) and the sample size (100, 150, 250, 450, 650, 850) of the simulated models. According to the main results, C2 index always shows a bigger Type I error than RMSEA, regardless of the experimental factors analysed. Finally, different action alternatives are discussed and future research lines are presented.

show abstract

Section: Discussionunclassified

Análisis factorial confirmatorio. Recomendaciones sobre mínimos cuadrados no ponderados en función del error Tipo I de Ji-Cuadrado y RMSEA

et al. 2015

View full text Add to dashboard Cite

show abstract

“…The factors (variables) identified in the EFA were treated as latent variables in the CFA. The model was estimated with a weighted least square mean and variance (WLSMV) adjusted estimator as a suitable estimator for ordinal data because it does not assume that the data is normally distributed [ 65 , 66 , 67 ]. We evaluated model goodness-of-fit to the data using multiple indices and the recommendations in Kline [ 57 ].…”

Section: Methodsmentioning

confidence: 99%

Perceived Risk and Intentions to Practice Health Protective Behaviors in a Mining-Impacted Region

Cooper

Langman

Sarathchandra

et al. 2020

IJERPH

View full text Add to dashboard Cite

Effective risk communication strategies are critical to reducing lead exposure in mining-impacted communities. Understanding the strength of the associations between perceived risk and individuals’ behavioral intentions to protect their health is important for developing these strategies. We conducted a survey within three communities of northern Idaho, USA (n = 306) in or near a Superfund Megasite with legacy mining contamination. Survey data were used to test a theoretical model based on the Health Belief Model. Respondents had higher intentions to practice health protective behaviors when they perceived the risk of lead contamination as severe and recognized the benefits of practicing health protective behaviors. Women reported higher behavioral intentions than men, but age and mining affiliation were not significantly associated with behavioral intentions. Although managing lead hazards in communities impacted by mining is challenging due to widely distributed contamination, effective health risk messages, paired with remediation, are powerful tools to protect the health and safety of residents.

show abstract

“…To derive factor score weights for subsequent regression analysis, CFA was replicated in Amos (Arbuckle, J.L. (2006) Amos Version 25.0, Chicago: SPSS, USA) using asymptotically distribution-free estimation on raw data (polychoric correlation functionality unavailable), an appropriate technique for ordinal, non-normal data, small models and large sample sizes (>1000) [ 41 ]. Item loadings and fit statistics were comparable across the two estimation methods ( Appendix B ).…”

Section: Methodsmentioning

confidence: 99%

Belonging and Inclusivity Make a Resilient Future for All: A Cross-Sectional Analysis of Post-Flood Social Capital in a Diverse Australian Rural Community

Matthews

Longman

Bennett–Levy

et al. 2020

IJERPH

View full text Add to dashboard Cite

In 2017, marginalised groups were disproportionately impacted by extensive flooding in a rural community in Northern New South Wales, Australia, with greater risk of home inundation, displacement and poor mental health. While social capital has been linked with good health and wellbeing, there has been limited investigation into its potential benefits in post-disaster contexts, particularly for marginalised groups. Six months post-flood, a cross-sectional survey was conducted to quantify associations between flood impact, individual social capital and psychological distress (including probable post-traumatic stress disorder). We adopted a community-academic partnership approach and purposive recruitment to increase participation from socio-economically marginalised groups (Aboriginal people and people in financial hardship). These groups reported lower levels of social capital (informal social connectedness, feelings of belonging, trust and optimism) compared to general community participants. Despite this, informal social connectedness and belonging were important factors for all participant groups, associated with reduced risk of psychological distress. In this flood-prone, rural community, there is a pressing need to build social capital collectively through co-designed strategies that simultaneously address the social, cultural and economic needs of marginalised groups. Multiple benefits will ensue for the whole community: reduced inequities; strengthened resilience; improved preparedness and lessened risk of long-term distress from disaster events.

show abstract

Structural equation modeling with ordinal variables: a large sample case study

Cited by 15 publications

References 15 publications

Análisis factorial confirmatorio. Recomendaciones sobre mínimos cuadrados no ponderados en función del error Tipo I de Ji-Cuadrado y RMSEA

Análisis factorial confirmatorio. Recomendaciones sobre mínimos cuadrados no ponderados en función del error Tipo I de Ji-Cuadrado y RMSEA

Perceived Risk and Intentions to Practice Health Protective Behaviors in a Mining-Impacted Region

Belonging and Inclusivity Make a Resilient Future for All: A Cross-Sectional Analysis of Post-Flood Social Capital in a Diverse Australian Rural Community

Contact Info

Product

Resources

About