Registry · Priors

construct.training predicts construct.training_performance

normal · informative · 5 studies · N = 30,462

Distribution

normal prior
Prior PDF · normalnormal distribution. normal prior. 95% CI ≈ [0.543, 0.785]; mean ≈ 0.664.0.4180.5410.6640.7870.910x0density

mean ≈ 0.664 · 95% CI ≈ [0.543, 0.785]

Intervals

Confidence interval (95%) — uncertainty about the mean ρ
[0.50, 0.66]
Credibility interval (95%) — distribution of the true effect across settings (the Bayesian prior)
[0.44, 0.69]
I² (heterogeneity) — share of total variance from between-study differences
47%

The true effect varies across settings — moderators likely matter.

SD_ρ>0 — true effect varies across settings; likely moderated (observed-score scale until artifact correction, PRN-058)

Evidence provenance

published ρ=0.58 (k=5, replication: meta-analytic); no primary-deployment evidence yet

Sourceρ (r)Scope
Published literature0.58k = 5 · N = 30,462

No primary-deployment evidence yet — this prior rests on published literature alone. As anonymized, aggregated effect sizes from real deployments are contributed, they appear here as a distinct, publication-bias-free source, fused with the literature into a posterior estimate.

Code

Drop this prior straight into your model. Snippets generated from the synthesized distribution + parameters.

target += normal_lpdf(beta | 0.664, 0.0616117);
beta = pm.Normal("beta", mu=0.664, sigma=0.0616117)
brms::prior(normal(0.664, 0.0616117), class = "b")
# base R sample
rnorm(N, mean = 0.664, sd = 0.0616117)
np.random.normal(loc=0.664, scale=0.0616117, size=N)

Parameters

FamilyParameters
normalI2 = 0.4731, mu = 0.6640, sigma = 0.06161, k_studies = 5.000, tau_squared = 0.008980

Synthesis

Method
random_effects_meta
Informativeness
informative
Replication status
meta-analytic
k_studies
5
n_total
30,462
Last updated
2026-05-31T01:07:49.275Z

Quality distribution

GradeCount
A5
B0
C0
D0

Contributing effect sizes

Effect-size detail pages land with a later sub-ticket; for now, ids link to the filtered list. Browse all rows via /registry/effects.