Registry · Priors

construct.safety_compliance predicts construct.accidents

normal · informative · 2 studies · N = 12,096

Distribution

Storage scale (Fisher z)
Prior PDF · normalnormal distribution. Storage scale (Fisher z). 95% CI ≈ [-0.235, -0.115]; mean ≈ -0.175.-0.298-0.237-0.175-0.114-0.0525z0density

mean ≈ -0.175 · 95% CI ≈ [-0.235, -0.115]

Reader scale (r)
Prior PDF · normalnormal distribution. Reader scale (r). 95% CI ≈ [-0.232, -0.115]; mean ≈ -0.174.-0.293-0.233-0.174-0.114-0.0544r0density

mean ≈ -0.174 · 95% CI ≈ [-0.232, -0.115]

Intervals

Confidence interval (95%) — uncertainty about the mean ρ
[-0.23, -0.11]
Credibility interval (95%) — distribution of the true effect across settings (the Bayesian prior)
[-0.25, -0.10]
I² (heterogeneity) — share of total variance from between-study differences
84%

The true effect is ~constant across settings — it generalizes.

SD_ρ≈0 — true effect is ~constant across settings; generalizes (observed-score scale until artifact correction, PRN-058)

Evidence provenance

published ρ=-0.17 (k=2, high heterogeneity (I²=0.84)); no primary-deployment evidence yet

Sourceρ (r)Scope
Published literature-0.17k = 2 · N = 12,096

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 | -0.175288, 0.0307093);
beta = pm.Normal("beta", mu=-0.175288, sigma=0.0307093)
brms::prior(normal(-0.175288, 0.0307093), class = "b")
# base R sample
rnorm(N, mean = -0.175288, sd = 0.0307093)
np.random.normal(loc=-0.175288, scale=0.0307093, size=N)

Parameters

FamilyParameters
normalI2 = 0.8367, mu = -0.1753, sigma = 0.03071, r_mean = -0.1735, k_studies = 2.000, tau_squared = 0.001598

Synthesis

Method
random_effects_meta
Informativeness
informative
Replication status
meta-analytic
k_studies
2
n_total
12,096
Last updated
2026-05-30T23:52:05.553Z

Quality distribution

GradeCount
A2
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.