Longitudinal partial strong measurement invariance of the four-item self-efficacy survey justifies fitting growth models to its scores¶

Claim · All claims
Evidence · 1 study · associational r2 · q2
Currency · newest study 2019 · not yet checked against its sources · not reviewed by a person · overdue for a recheck since 2022: tool and model accuracy changes quickly

Subclaims¶

q2 i? Configural and weak invariance held; strong invariance showed a significant fit decrement traced to three threshold constraints, and the partial strong model (RMSEA = .02) was preferred. → Soland 2019

Evidence¶

Soland 2019¶

Soland, J. (2019). English Language Learners, Self-efficacy, and the Achievement Gap: Understanding the Relationship between Academic and Social-emotional Growth (The Collaborative for Student Growth at NWEA Working Paper). https://www.nwea.org/research/publication/english-language-learners-self-efficacy-and-the-achievement-gap-understanding-the-relationship-between-academic-and-social-emotional-growth/

q2 · i? · associational · r2

Longitudinal measurement invariance testing (Appendix C, Table A5) following Widaman, Ferrer, and Conger, with time periods as groups. Weak invariance constraints improved fit with non-significant LRTs; strong invariance produced a significant LRT decrement traced to three threshold constraints. No effect size is printed.

"Given the model fit was excellent for partial invariance (RMSEA = .02), the partial model became the preferred model for subsequent analyses. Ultimately, these results indicate that fitting a growth model to the self-efficacy scores is justifiable."

Discussion¶

Related Claims¶

• Prior longitudinal studies of math and self-efficacy tend to fit models assuming the constructs lack unique developmental trajectories and do not examine within-person relations — related
• Establishing longitudinal factorial invariance is neither sufficient nor necessary for examining developmental change — related
• The authors conclude that MAP reading and mathematics CAT constructs are invariant across five time points in ten states (except Indiana mathematics), though their mathematics tables show strong-invariance CFI drops above 0.01 in most states — related
• MLGM model fit failed for the Indiana mathematics test, the sole exception to invariance support — related
• The GenAI-SRL scale achieves measurement invariance across gender groups at metric and scalar levels — related
• A companion working paper examines the relationship between academic and social-emotional growth for English Language Learners — a broader claim this one bears on
• An NWEA research brief examines how self-efficacy relates to the persistence of achievement gaps for English Language Learners; its landing page states no finding — related
• Configural and metric measurement invariance across time hold for nearly all constructs, but scalar invariance is problematic for several — related