Bayesian network modeling ITS showed a higher weighted mean effect size than model tracing and constraint-based modeling, but only under a fixed-effect model¶
Claim · All claims
Evidence · 1 study · quant-synthesisr2·q4
Currency · newest study 2014 · 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.
q4 i? Under a random-effects model, model tracing, Bayesian network modeling, and other types of ITS produced statistically significant effect sizes while constraint-based modeling and expectation and misconception tailoring did not; the higher mean for Bayesian network modeling was significantly greater than model tracing and constraint-based modeling only under a fixed-effect model. → Wenting Ma 2014
Evidence¶
Wenting Ma 2014¶
Wenting Ma, Olusola O. Adesope, John C. Nesbit, and Qing Liu. (2014). Intelligent Tutoring Systems and Learning Outcomes: A Meta-Analysis. Journal of Educational Psychology. https://doi.org/10.1037/a0037123
q4 · i? · quant-synthesis · r2
Type-of-ITS moderator analysis (Table 2). Random-effects means: Bayesian network modeling g = .54 (k = 10), model tracing g = .35 (k = 21), expectation and misconception tailoring g = .34 (k = 3), constraint-based modeling g = .24 (k = 7). Fixed-effect between-levels difference was significant, QB(5) = 36.37, p < .001, with Bayesian network modeling significantly higher than model tracing and constraint-based modeling in post hoc analyses.
"A lthough IT S w ith B ayesian netw ork m o deling pro duced a higher w eighted m ean effect size (g - .54) than m odel tracing (g = .35), constraint-based m odeling (g = .24), and ex pectation and m isconception tailoring (g = .34), th e betw een- levels difference w as no t statistically significant under a random - effects m odel."
Discussion¶
Related Claims¶
- Learning with intelligent tutoring systems yields a moderate, statistically significant overall advantage in achievement over non-ITS modes of instruction — a broader claim this one bears on
- ITS produce significant positive effects at all grade levels and in almost all subject domains evaluated, with exceptions such as chemistry — related
- Against no-treatment controls, ITS produce a large statistically significant effect (g = 1.23) under a random-effects model — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
its-type-bayesian-higher-than-model-tracing-fixed-effect |
title |
Bayesian network modeling ITS showed a higher weighted mean effect size than model tracing and constraint-based modeling, but only under a fixed-effect model |
description |
Bayesian network modeling ITS showed a higher weighted mean effect size than model tracing and constraint-based modeling, but only under a fixed-effect model |
status |
review |
evidence_strength |
mixed |
newest_evidence |
2014 |
generated |
by process:wiki-ingest on 2026-10-13 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — wenting-ma-2014 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.