The Effect of Estimation Methods on SEM Fit Indices

2019/11/10 by Dexin Shi, Alberto Maydeu-Olivares, Alberto Maydeu‐Olivares · 393 citations
Decision Sciences · Mathematics · Psychology · #Algorithm #Behavioral Health and Interventions #Econometrics #Estimator #Goodness of fit #Mathematics #Mean squared error #Multi-Criteria Decision Making #Population #Psychometric Methodologies and Testing #Residual #Statistics #Structural equation modeling

paper · pdf · doi:10.1177/0013164419885164

published in Educational and Psychological Measurement 80(3), 421-445 (SAGE Publishing)

openalex publication_date 2019/11/10 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/04

Abstract

We examined the effect of estimation methods, maximum likelihood (ML), unweighted least squares (ULS), and diagonally weighted least squares (DWLS), on three population SEM (structural equation modeling) fit indices: the root mean square error of approximation (RMSEA), the comparative fit index (CFI), and the standardized root mean square residual (SRMR). We considered different types and levels of misspecification in factor analysis models: misspecified dimensionality, omitting cross-loadings, and ignoring residual correlations. Estimation methods had substantial impacts on the RMSEA and CFI so that different cutoff values need to be employed for different estimators. In contrast, SRMR is robust to the method used to estimate the model parameters. The same criterion can be applied at the population level when using the SRMR to evaluate model fit, regardless of the choice of estimation method.

Citations

• Understanding the Model Size Effect on SEM Fit Indices

Cited by

• Evaluating Close Fit in Ordinal Factor Analysis Models With Multiply Imputed Data
• PLS-SEM and reflective constructs: A response to recent criticism and a constructive path forward
• CB-SEM vs PLS-SEM methods for research in social sciences and technology forecasting
• Direct Discrepancy Dynamic Fit Index Cutoffs for Arbitrary Covariance Structure Models
• The association of dispositional anxiety with the NoGo N2 under relaxation instruction vs. speed/accuracy instruction
• Factors Shaping the Adoption of AI Tools among Gen Z: An Extended UTAUT2 Model Investigation Using CB-SEM
• The mediating roles of resilience and motivation in the relationship between students’ English learning burnout and engagement: a conservation-of-resources perspective
• Children’s executive function during the COVID-19 pandemic in Argentina: Associations with home literacy, reading, and screen times
• Assessing mental well-being in a Sinhala speaking Sri Lankan population: validation of the WHO-5 well-being index. [europepmc]
• How perceived threat of COVID-19 related to aggressive tendencies during the pandemic in Hubei Province and other regions of China: Mediators and moderators. [europepmc]
• A trouble shared is a trouble halved: The role of family identification and identification with humankind in well-being during the COVID-19 pandemic. [europepmc]
• Brief Report: The Broad Autism Phenotype in Swedish Parents of Children With and Without Autism Spectrum Conditions. [europepmc]
• Psychometrics of three Swedish physical pediatric item banks from the Patient-Reported Outcomes Measurement Information System (PROMIS)®: pain interference, fatigue, and physical activity. [europepmc]
• Factors Affecting the Extent of Patients' Electronic Medical Record Use: An Empirical Study Focusing on System and Patient Characteristics. [europepmc]
• Bone and Lean Mass Loss and Cognitive Impairment for Healthy Elder Adults: Analysis of the Nutrition and Health Survey in Taiwan 2013-2016 and a Validation Study With Structural Equation Modeling. [europepmc]
• Measurement Invariant but Non-Normal Treatment Responses in Guided Internet Psychotherapies for Depressive and Generalized Anxiety Disorders. [europepmc]
• Key Predictors of Primary Care Providers' Self-Efficacy in Caring for Children with Overweight or Obesity. [europepmc]
• How Accurate Is Your Correlation? Different Methods Derive Different Results and Different Interpretations. [europepmc]
• Measurement Invariance of the Bergen Social Media Addiction Scale Across Genders. [europepmc]
• Psychometric Assessment and Gender Invariance of the Polish Version of the Gaming Disorder Test. [europepmc]
• Drivers of the Intention to Receive a COVID-19 Booster Vaccine: Insights from the UK and Australia. [europepmc]
• Validation of the brief instrument "Health Literacy for School-Aged Children" (HLSAC) among Norwegian adolescents. [europepmc]
• Review of the psychometric properties of the Patient Health Questionnaire-9 (PHQ-9) Spanish version in a sample of Puerto Rican workers. [europepmc]
• The Swedish Version of the eHealth Literacy Questionnaire: Translation, Cultural Adaptation, and Validation Study. [europepmc]
• Psychometric testing of the Swedish version of the measure of moral distress for healthcare professionals (MMD-HP). [europepmc]
• Validation of the Spanish version of the eating disorders quality of life instrument (EDQOL). [europepmc]
• Implementing alternative estimation methods to test the construct validity of Likert-scale instruments. [europepmc]
• Why we need to abandon fixed cutoffs for goodness-of-fit indices: An extensive simulation and possible solutions. [europepmc]
• The role of teachers' socio-emotional competence in reducing burnout through increased work engagement. [europepmc]
• Psychometric validation of the Hospital Anxiety and Depression Scale (HADS) in community-dwelling older adults. [europepmc]
• Development of the Mentoring in Undergraduate Research Survey. [europepmc]
• Sensory processing sensitivity as a predictor of health-related quality of life outcomes via stress and sleep quality. [europepmc]
• Motivation to Clinical Trial Participation: Health Information Distrust and Healthcare Access as Explanatory Variables and Gender as Moderator. [europepmc]

Related

• Understanding the Model Size Effect on SEM Fit Indices
• Detecting Misspecified Multilevel Structural Equation Models with Common Fit Indices: A Monte Carlo Study
• Assessing the Size of Model Misfit in Structural Equation Models
• An Investigation of the Sample Performance of Two Nonnormality Corrections for RMSEA
• The Performance of RMSEA in Models With Small Degrees of Freedom