Theoretical ranges differ sharply: L with self-transitions removed is bounded below by −1 (individual base rates) or −2 (averaged), while L* is bounded by −k+1 (individual) or has no finite lower bound (averaged)¶
Claim · All claims
Evidence · 1 study · theoreticalr3·q2
Currency · newest study 2020 · not yet checked against its sources · not reviewed by a person · overdue for a recheck since 2023: tool and model accuracy changes quickly
Subclaims¶
Reading the evidence codes
q is the design tier, i the impact, n the sample, and the kind with its r
the rigour judged within that kind: what each code means.
This claim: no standardized effect is recorded in observations/ for it yet, so no benchmark reading is possible.
q2 i? The minimum values of L and L* depend on both the statistic used and the base-rate computation procedure, as established by Theorems 3–6. → Jeffrey Matayoshi and Shamya Karumbaiah 2020
Evidence¶
Jeffrey Matayoshi and Shamya Karumbaiah 2020¶
Jeffrey Matayoshi and Shamya Karumbaiah. (2020). Adjusting the L Statistic when Self-Transitions are Excluded in Affect Dynamics. Journal of Educational Data Mining, Volume 12, No 4. https://jedm.educationaldatamining.org/index.php/JEDM/article/view/478
q2 · i? · theoretical · r3
Mathematical derivation (Theorems 3–6) establishing: L ranges [−1, 1] or [−2, 1] with self-transitions removed (individual vs averaged base rates); L* ranges [−k+1, 1] or (−∞, 1] with transitions to A removed. Maximum value is 1 for both statistics.
"The results show that the minimum values differ greatly based on the statistic used (L or L∗), as well as the procedure used to compute the base rates (per sequence or over all sequences)."
Discussion¶
Related Claims¶
- On real student data, L with self-transitions removed makes all transitions from flow appear positive and significant, while L* gives a mix of signs with the only significant value negative — related
- Simulations show L* values at chance stay centered at zero even when one affective state's base rate is disproportionately high — related
- Simulations with two dominant base rates also show L* at chance centered at zero — related
- When self-transitions are excluded, the L statistic's chance value becomes 1/(n−1)² for a state space with n affective states, so past L results excluding self-transitions were likely misinterpreted — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
l-and-l-star-theoretical-value-ranges |
title |
Theoretical ranges differ sharply: L with self-transitions removed is bounded below by −1 (individual base rates) or −2 (averaged), while L* is bounded by −k+1 (individual) or has no finite lower bound (averaged) |
description |
Theoretical ranges differ sharply: L with self-transitions removed is bounded below by −1 (individual base rates) or −2 (averaged), while L* is bounded by −k+1 (individual) or has no finite lower bound (averaged) |
status |
review |
evidence_strength |
moderate |
newest_evidence |
2020 |
recheck_by |
2023 |
generated |
by process:wiki-ingest on 2026-10-08 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — jeffrey-matayoshi-and-shamya-karumbaiah-2020 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.