feat(psychometric): recover Driver lagged covariance of predetermined T0VAR - #182
Conversation
|
Important Draft PR not reviewedDraft PRs are not automatically reviewed by default.
To automatically review draft PRs, update your CodeRabbit configuration: reviews:
auto_review:
drafts: trueThanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
542806b to
96e8d1c
Compare
… T0VAR
Map the Driver, Oud, and Voelkle (2017, Eq. 3–5 of §4.3 predetermined
first occasion) lagged covariance of free T0VAR as
trait + e^{aΔt} p_0 + (B/a)²v. Trait and addedTIPREDVAR do not
decay. Setting p_0 = −q/(2a) recovers the stationary lagged map.
Stationary lagged covariance, later-occasion variance, the decayed
total, and p_0 itself remain refused as this composition. Observed
lagged covariance is λ² of that map plus ψ. Independent ε_t does
not enter. A zero-diffusion carry with a ≥ 0 is kept.
2d4d6bf to
7e20397
Compare
Review update
|
|
Folded into the consolidation vehicle #231; this draft stays open until the vehicle merges, then closes as superseded-by-consolidation. |
|
Superseded by consolidation: this slice's Driver et al. (2017) standardization recovery landed on protected main through the integration vehicles (#231/#232), and its contract coverage is carried by the reconciled suites (multilevel_event_time_recovery_contract, rubin_and_mean_gate_contract) with test-signature repair tracked in #234. The stacked-draft form is retired to keep the delivery queue at review-ready work only; no capability is lost — the exact-head provenance remains in the vehicle PR descriptions and CHANGELOG. |
Stacked on #181 (
542806b) / #49 (6f95142). ADR 0005 executable slice stays insidepsychometric_core. This is not a second invariance crate and does not recreate #78 or #80.psychometric_corerecovers the Driver, Oud, and Voelkle (2017, §4.3, pp. 9–10; Eq. 3–5, pp. 4–5; Table 2, p. 12; p. 16; §7.2, pp. 20–21; JSS PDF re-opened 2026-08-23T09:04Z from https://www.jstatsoft.org/index.php/jss/article/download/v077i05/1104) scalar lagged covariance of §4.3 predeterminedT0VAR. Section 4.3 treats the first time point as predetermined when no assumptions are made about the process prior to the initial time point. FreeT0VARp_0is then estimated.Equation 3 writes
η(t) = exp(A Δt) η(t0) + …. Equation 4 writescov(η_t, η_{t-1}) = A_Δt cov(η_{t-1}). Trait variance andaddedTIPREDVARare time-invariant between-subject and do not decay withe^{a Δt}. The lagged composition istrait + e^{a Δt} p_0 + (B / a)² v. Form the lagged free first-occasion covariance first, then include the trait, then include the TI extra variance, then add.p_0 = −q / (2 a)recovers the stationary lagged map.−q / (2 a)in place ofp_0and is not this map whenp_0is free.trait + p_0 + (B / a)² vas if it were all state is not this map.T0VARp_0is not this map.Q_Δtand is not this map.Δt → ∞with stablea < 0the state term vanishes.Δt → 0+the composition approachestrait + p_0 + (B / a)² v.a ≥ 0ise^{a Δt} p_0and is kept.Equation 5 of that lagged covariance is
λ²(trait + e^{a Δt} p_0 + (B / a)² v) + ψ. Independentε_tdoes not enter.MANIFESTVARis not that lagged observed covariance. The predetermined lagged latent covariance is not the predetermined lagged observed covariance. Predetermined later observed variance includesQ_Δtandθand is not that lagged observed covariance. Stationary lagged observed covariance is not that observed covariance whenp_0is free.Still not a Kalman filter, not a matrix
expm, not ESEM estimation, not DSEM, and not ctsem estimation. Meredith (1993) remains unread (Unpaywall 2026-08-23T09:04Z:is_oa: false; title Measurement Invariance, Factor Analysis and Factorial Invariance). Mislevy (1991, Psychometrika, 56, 177–196) remains unread (Unpaywall 2026-08-23T09:04Z:is_oa: false; title Randomization-Based Inference about Latent Variables from Complex Samples).Do not merge, self-approve, or request Copilot.