Skip to content

L* statistic

Research Method · All research methods
Evidence · 1 claim (1 for) · 1 study (1 theoretical), q2 · 0 of 1 report an effect size · 1 claim rests on one study

Description

L* is a modified version of D'Mello's L statistic intended for use when self-transitions are excluded. It restricts computation to transitions in T_A, the set where the next state is not A, and normalizes the base rates so that, per Theorem 1, "the value of L∗ at chance is equal to zero" when conditional independence holds. The article proves this result and compares L's properties to L. L is equivalent to the λ statistic of Bosch and Paquette (2020) when base rates are computed per sequence, but distinct when averaged over a sample.

Accounts

  • L*: a modified L statistic that restores a zero chance value when self-transitions are excluded**: L is a modified version of D'Mello's L statistic intended for use when self-transitions are excluded. It restricts computation to transitions in T_A, the set where the next state is not A, and normalizes the base rates so that, per Theorem 1, "the value of L∗ at chance is equal to zero" when conditional independence holds. The article proves this result and compares L's properties to L. L* is equivalent to the λ statistic of Bosch and Paquette (2020) when base rates are computed per sequence, but distinct when averaged over a sample. (Jeffrey Matayoshi et al. (2020))

Claims

-

Key Sources

  • 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
Page metadata
Field Value
type research-method
id l-statistic
title L* statistic
description L* is a modified version of D'Mello's L statistic intended for use when self-transitions are excluded.
status review
moved_from theory/l-star-modified-transition-metric
generated by process:sweep-kinds on 2026-10-10
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.