Adding lag-2 paths to CLPMs substantially improves fit and provides stronger controls for preexisting differences, positioning extended CLPMs as viable alternatives to RI-CLPMs¶

Claim · All claims
Evidence · 1 study · associational r2 · q2
Currency · newest study 2022 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? Prior research cited by the review shows lag-2 paths substantially improve CLPM fit and strengthen control for confounding, so goodness-of-fit ceases to be a critical issue in comparing RI-CLPMs and extended CLPMs. → Herbert W. Marsh 2022

Evidence¶

Herbert W. Marsh 2022¶

Herbert W. Marsh, Reinhard Pekrun, & Oliver Lüdtke. (2022). Directional Ordering of Self-Concept, School Grades, and Standardized Tests Over Five Years: New Tripartite Models Juxtaposing Within- and Between-Person Perspectives. Educational Psychology Review. https://doi.org/10.1007/s10648-022-09662-9

q2 · i? · associational · r2

The review attributes this to Marsh et al. (2018a, 2018b) and Lüdtke & Robitzsch (2021), who showed with simulated data that CLPMs with lag-2 effects fit as well as RI-CLPMs. Reported as second-hand evidence, not this study's own analysis.

"Marsh and et al., (2018a, 2018b, p. 271; also see Lüdtke & Robitzsch, 2021) argued that the addition of lag-2 paths substantially improved the fit of a CLPM and served for "providing stronger controls for preexisting differences.""

Discussion¶

Related Claims¶

• Simulation evidence shows RI-CLPM estimates are biased when the true model is a CLPM with lag-2 effects, and fit statistics cannot decide between the two — reports the opposite
• RI-CLPMs control unmeasured time-invariant covariates better than CLPMs, but neither controls unmeasured time-varying covariates well — related
• Across basic and extended RI-CLPMs and CLPMs of five-wave secondary-school data, math self-concept and achievement show consistent reciprocal (bidirectional) directional ordering — related
• Reanalyses of simulated and PALMA data provide converging support for the extended reciprocal effects model, including an effect of academic self-concept on achievement — related
• The extended REM was robust to several alternative modeling specifications proposed by Sorjonen et al. — related
• The alternative models proposed by Sorjonen et al. relied on specifications that raised model-validity concerns or did not fully capture the extended REM's temporal structure — related
• With young primary-school readers, REM support appeared in CLPMs but not RI-CLPMs, motivating tests with older students — related
• In German secondary-school mathematics, effects of self-concept on achievement are lagged (lag1) whereas effects of achievement on self-concept are more contemporaneous (lag0) — related
• Random-intercept and lag2 panel models rest on different assumptions and offer alternative perspectives on controlling covariates — related
• The reciprocal effects are robust to alternative models attributing them to latent confounding or residual error (RI-LTVC, STARTS) — related
• Reciprocal effects are robust to time-invariant confounders, but the French lagged self-concept effect did not survive the lag2 carryover stress test — related
• The choice of longitudinal statistical model can determine whether reciprocal motivation-achievement relations are found — related
• RI-CLPM random-intercept correlations between grades and emotions (median |r| = 0.46) were stronger than the undecomposed CLPM correlations (median |0.34|) — related
• Deviations from the convergence assumption produce unreliable cross-lagged findings in school motivation research — related
• Next-generation cross-lagged models relax the convergence assumption in school motivation panel data — related