Positive school-average achievement effects on subsequent achievement can be phantom effects that disappear under doubly-latent modeling with covariates¶

Claim · All claims
Evidence · 1 study · associational r3 · q2
Currency · newest study 2023 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? The article argues that apparently positive school-average achievement effects on subsequent achievement can reflect failure to control measurement error and preexisting differences, citing Harker and Tymms (2004) and recent doubly-latent studies. → Marsh 2023

Evidence¶

Marsh 2023¶

Marsh, H. W., Pekrun, R., Dicke, T., Guo, J., Parker, P. D., & Basarkod, G. (2023). Disentangling the Long-Term Compositional Effects of School-Average Achievement and SES: a Substantive-Methodological Synergy. Educational Psychology Review. https://doi.org/10.1007/s10648-023-09726-4

q2 · i? · associational · r3

Narrative review section attributing this argument to Harker and Tymms (2004) and recent doubly-latent studies (e.g., Dicke et al., 2018; Becker et al., 2022). The article defines "phantom effects" as positive bias due to uncontrolled measurement error and preexisting differences.

"Here, we use the term phantom effects to represent the positive bias in apparently positive effects of school-average achievement that are actually due to the failure to control for measurement error and preexisting differences."

Discussion¶

Related Claims¶

• Measurement error bias inflates peer spillover effects while attenuating the BFLPE; controls strengthen the BFLPE and weaken the spillover effect — related
• Positive class-level peer spillover effects on mathematics achievement fail to replicate once measurement error is controlled with doubly latent models — possibly the same claim (merge candidate)
• When compositional effects are constrained equal across countries, the overall peer spillover effect is negative and non-significant while the BFLPE remains negative and significant — related
• Doubly latent multilevel structural equation models disaggregate disciplinary-problem effects at student versus classroom level — related