Registry · Priors

construct.general_mental_ability_gma predicts construct.task_performance

normal · weakly_informative · 4 studies · N = 75,953

Distribution

Storage scale (Fisher z)
Prior PDF · normalnormal distribution. Storage scale (Fisher z). 95% CI ≈ [0.148, 0.526]; mean ≈ 0.337.-0.04900.1440.3370.5300.723z0density

mean ≈ 0.337 · 95% CI ≈ [0.148, 0.526]

Reader scale (r)
Prior PDF · normalnormal distribution. Reader scale (r). 95% CI ≈ [0.156, 0.494]; mean ≈ 0.325.-0.02040.1520.3250.4980.670r0density

mean ≈ 0.325 · 95% CI ≈ [0.156, 0.494]

Weakly informative prior. This prior is weakly informative. It will nudge your posterior but won't overwhelm it; expect data to do most of the work in modest samples.

Intervals

Confidence interval (95%) — uncertainty about the mean ρ
[0.15, 0.48]
Credibility interval (95%) — distribution of the true effect across settings (the Bayesian prior)
[-0.01, 0.59]
I² (heterogeneity) — share of total variance from between-study differences
100% — the contributing studies disagree almost completely; read the pooled value as a midpoint of conflicting findings, not as one population's effect

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=0.33 (k=4, high heterogeneity (I²=1.00)); no primary-deployment evidence yet

Sourceρ (r)Scope
Published literature0.33k = 4 · N = 75,953

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 | 0.337236, 0.0965572);
beta = pm.Normal("beta", mu=0.337236, sigma=0.0965572)
brms::prior(normal(0.337236, 0.0965572), class = "b")
# base R sample
rnorm(N, mean = 0.337236, sd = 0.0965572)
np.random.normal(loc=0.337236, scale=0.0965572, size=N)

Parameters

FamilyParameters
normalI2 = 0.9974, mu = 0.3372, sigma = 0.09656, r_mean = 0.3250, k_studies = 4.000, tau_squared = 0.03057, fisher_z_bias = 0.003181, r_mean_bare_bones = 0.3218

Synthesis

Method
random_effects_meta
Informativeness
weakly_informative
Replication status
meta-analytic
k_studies
4
n_total
75,953
Last updated
2026-07-16T01:08:08.784Z

Quality distribution

GradeCount
A3
B1
C0
D0

Source articles

The research this prior is synthesized from — each is a full dossier (findings, the models it informs, and what the literature says).

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.