cvprofiles · construct-validity profile

Trust — cells (country-demeaned)

Admissible measurement set under a stated nomological network, and the image of β on that set. Empty sets and wide ranges are scientific features.

Empty admissible set — success, not a crash

Under this network and thresholds, no candidate measure survives. The engine is not broken: the theory + data reject the whole menu. Reported range is undefined; do not auto-loosen θ.

Construct-identified range

[L, U] · method = min/max B*

∅  empty M*

No survivors → no image of β. Inference diagnostics are additive and never loosen θ.

Target β = corr_y on outcome gps_trust_cell. Range uses only measures in M*; rejected β values are shown below but never enter [L,U].

Run freeze

run_id70f49c7b102be3aea7504a0d7d2e3f0e102ffb6b80d31ff72d6d8fd55b99f6cf
package3.0.2
scores_hash5338e3e4ccec220a8da6b2ab30559ef5e1bb7cc13e99e6a29098cf5f152e8c25
network_hash55f9b1ac9fa6bd3cbc4bc9f3150b0f2669fe1edfd5beb7bf754f89767f3f8f74
beta_hash19fe88c41c4644897cee8c770b625bd57adbae206e1efc2774599c116eacd51e
δ0.0
seed20260814
networktrust_cells_two_resolution

Bootstrap inference · additive to headline range

Units-only Efron resampling; percentile band over non-empty replicates. The headline [L, U] above remains min/max β(M*) on the full sample.

replicates1000
seed20260814
quantiles[0.025, 0.975]
non-empty0
empty1000 (1.000)
degenerate0 (0.000)
band∅

all replicates empty (or degenerate): band is null; headline [L,U] unchanged

Uncertainty band · additive to headline range

Per-side α/2 quantiles over non-empty bootstrap replicates (α = 0.1). Heuristic band — not a confidence interval, not a holdout-robustness band. The headline [L, U] above remains min/max β(M*) on the full sample.

α0.1
κ2.0
quantiles[0.05, 0.95]
band∅
empty rate1.000
degenerate rate0.000

Admission frequency p̂m

measurep̂m
m_trust_general —
m_trust_in_group —
m_trust_out_group —
m_trust_institution —
m_trust_composite —
m_noise —

all replicates empty (or degenerate): uncertainty band is null; boundary set empty; admission frequencies null. Heuristic band — not a confidence interval and not a holdout-robustness band.

θ-grid sensitivity · diagnostic viewport

λ scales threshold magnitudes only. λ is never auto-selected; the headline is always λ=1.0. This grid is not part of the freeze preimage.

λ|M*|emptyLU
0.5 0 yes — —
1.0 0 yes — —
1.5 0 yes — —
2.0 0 yes — —

θ-anchors · pre-data audit

One pre-data anchor per restriction (hash 07533ac8ce87…). The engine enforces completeness + hash; "pre-data" is a process commitment, not a temporal claim.

restrictionkindpre-dataanchor
conv_edu_cell literature yes falk2018_table_v — Same education implication applied within country (cell means). θ=0.20.
mono_edu_cell literature yes falk2018_table_v — Leftover within-country rank-monotone education restriction. θ=0.15.

Menu admission

M* size = 0 / 6. Slack rule: admit if sr(m) ≥ −δ for all r.

measure status β(m) failed restrictions
m_trust_general rejected 0.052428 conv_edu_cell
m_trust_in_group rejected 0.223931 conv_edu_cell
m_trust_out_group rejected 0.211423 conv_edu_cell
m_trust_institution rejected 0.284723 conv_edu_cell
m_trust_composite rejected 0.317611 conv_edu_cell
m_noise rejected 0.014662 conv_edu_cell

Slack matrix sr(m)

Positive / zero ≈ satisfied at δ=0.0. Negative = violation magnitude.

measure conv_edu_cell mono_edu_cell
m_trust_general -0.176854 -0.131341
m_trust_in_group -0.268407 -0.233353
m_trust_out_group -0.274989 -0.224794
m_trust_institution -0.627369 -0.552204
m_trust_composite -0.473703 -0.414333
m_noise -0.171912 -0.119007

Network (researcher-owned)

Engine does not invent restrictions. Agent may author oracle R for synthetic DGPs only.