Sensitivity analysis finds outcome gains significant at cut-points below 5 minutes and beyond 13-15 minutes of delayed start in both subjects¶
Claim · All claims
Evidence · 1 study · associationalr2·q2
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person
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? Cut-point analyses show significant effects for average delayed starts under 5 minutes (Math β=.14, p=.02; ELA β=.18, p<.01) and at 13 or 15 minutes in both subjects. → Jordan Gutterman 2026
Evidence¶
Jordan Gutterman 2026¶
Jordan Gutterman, Ashish Gurung, Lee Branstetter, Kenneth Koedinger, and Vincent Aleven. (2026). Cross-Subject Predictive Validity for Learning Outcomes of Delayed Start Behavior. https://arxiv.org/abs/2606.25308 doi:10.48550/arxiv.2606.25308
q2 · i? · associational · r2
Sensitivity analysis (Equation 2) testing dummy cut-points from 4 to 16 minutes: gains were "significant in both subject areas" below 5 minutes and at 13/15 minutes; ELA effects varied less (range .13-.17 SD for 7-14 min cut-points). Benjamini-Hochberg corrections retained significance.
"The cut-points with statistical significance in both subject areas were average delayed starts of less than 5 minutes (Mathβ= .14, p = .02; ELAβ= .18, p =<.01), and at less than 13 or 15 minutes (Mathβ= .16, .20, p = .02, .03; ELAβ= .15, .22, p = .03,<.01)."
Discussion¶
Related Claims¶
- Delayed start during math practice predicts standardized ELA test performance (β=.10 SD, p<.001) — related
- Delayed start during math practice predicts standardized math test performance (β=-.07 SD, p=.02) — related
- Classroom-relativized delayed start shows stronger predictive power and model fit than raw minutes, especially for ELA outcomes — related
- Gaussian Mixture Modeling identifies two latent clusters of delayed start behavior, outperforming three-cluster and unimodal models — related
- Early starters (<5 min delay) show greater outcome growth while chronic delayers (>13 min) show negative trends relative to regular starters — a broader claim this one bears on
- Total time on task in the DLP positively predicts both math and ELA outcomes — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
sensitivity-analysis-cutpoints |
title |
Sensitivity analysis finds outcome gains significant at cut-points below 5 minutes and beyond 13-15 minutes of delayed start in both subjects |
description |
Sensitivity analysis finds outcome gains significant at cut-points below 5 minutes and beyond 13-15 minutes of delayed start in both subjects |
status |
review |
evidence_strength |
moderate |
newest_evidence |
2026 |
generated |
by process:wiki-ingest on 2026-10-10 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — jordan-gutterman-2026 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.