cvprofiles · construct-validity profile
Admissible measurement set under a stated nomological network, and the image of β on that set. Empty sets and wide ranges are scientific features.
[L, U] · method = min/max B*
[0.402463, 0.402463]
Width = 0.000000 · point-ID · bootstrap percentile band = [-0.076983, 0.603115]
Target β = ols_coef on outcome log_gdp_pc. Range uses only measures in M*; rejected β values are shown below but never enter [L,U].
| run_id | be0f4841cadf5d3fb9412eef0d527f0fddb7e4a9af53391d68ef08b76649bf6b |
|---|---|
| package | 3.0.2 |
| scores_hash | ba400cce52f2dc214385323f88511d9914b15b6686b526f06a486126cc3b35c8 |
| network_hash | 3cdf089fbb4a9a419d4a89ad707d68a0f6cae96438fe43fba503403f2642ea66 |
| beta_hash | 40040c2105c1d9b34e212dddd8ca9487fdb315d4db2ebee0ebaf29129df5cafe |
| δ | 0.0 |
| seed | 20260814 |
| network | patience_country_two_resolution |
Units-only Efron resampling; percentile band over non-empty replicates. The headline [L, U] above remains min/max β(M*) on the full sample.
| replicates | 1000 |
|---|---|
| seed | 20260814 |
| quantiles | [0.025, 0.975] |
| non-empty | 703 |
| empty | 297 (0.297) |
| degenerate | 0 (0.000) |
| band | [-0.076983, 0.603115] |
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.
| α | 0.1 |
|---|---|
| κ | 2.0 |
| quantiles | [0.05, 0.95] |
| band | [0.078614, 0.562863] |
| empty rate | 0.297 |
| degenerate rate | 0.000 |
| measure | margin | SE | boundary |
|---|---|---|---|
| m_gps_patience | 0.075427 | 0.080189 | yes |
| m_wvs_q13 | -0.533164 | 0.122895 | no |
| m_wvs_q14 | -0.776779 | 0.094246 | no |
| m_composite | -0.721815 | 0.102045 | no |
| m_noise | -0.265491 | 0.156951 | yes |
| measure | p̂m |
|---|---|
| m_gps_patience | 0.979 |
| m_wvs_q13 | 0.000 |
| m_wvs_q14 | 0.000 |
| m_composite | 0.000 |
| m_noise | 0.053 |
Heuristic uncertainty band over non-empty bootstrap replicates (selection uncertainty on the pooled sample; holdout verdict is a full-sample point finding outside the band). Not a confidence interval; not a holdout-robustness band. Boundary attribution: |margin_m| <= kappa * SE_m.
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*| | empty | L | U |
|---|---|---|---|---|
| 0.5 | 0 | yes | — | — |
| 1.0 | 1 | no | 0.402463 | 0.402463 |
| 1.5 | 1 | no | 0.402463 | 0.402463 |
| 2.0 | 1 | no | 0.402463 | 0.402463 |
One pre-data anchor per restriction (hash e68030d19e06…). The engine enforces completeness + hash; "pre-data" is a process commitment, not a temporal claim.
| restriction | kind | pre-data | anchor |
|---|---|---|---|
| conv_edu | literature | yes | falk2018_schooling — Falk et al. 2018: country patience vs average years of schooling ρ=0.65 (p<.01); individual patience–education coefficient positive in >90% of countries. |
| disc_risk | literature | yes | falk2018_table_iv_hanushek2022 — Falk et al. 2018 Table IV Corr(patience, risktaking)=0.230 (n=76); Hanushek et al. 2022 r=0.358 (n=49). θ=0.35 admits the published range and rejects r≳0.6. |
| mono_edu | literature | yes | falk2018_schooling — Same human-capital implication as conv_edu, written as a leftover rank restriction (θ=0.15). |
M* size = 1 / 5. Slack rule: admit if sr(m) ≥ −δ for all r.
| measure | status | β(m) | failed restrictions |
|---|---|---|---|
| m_gps_patience | admissible | 0.402463 | — |
| m_wvs_q13 | rejected | -0.165988 | conv_edu |
| m_wvs_q14 | rejected | -0.194840 | conv_edu |
| m_composite | rejected | -0.218747 | conv_edu |
| m_noise | rejected | 0.019901 | conv_edu |
Positive / zero ≈ satisfied at δ=0.0. Negative = violation magnitude.
| measure | conv_edu | disc_risk | mono_edu |
|---|---|---|---|
| m_gps_patience | 0.275473 | 0.075427 | 0.233275 |
| m_wvs_q13 | -0.533164 | 0.058201 | -0.469512 |
| m_wvs_q14 | -0.776779 | 0.345857 | -0.697735 |
| m_composite | -0.721815 | 0.185041 | -0.678920 |
| m_noise | -0.265491 | 0.241430 | -0.237108 |
Engine does not invent restrictions. Agent may author oracle R for synthetic DGPs only.