Pre-registration
Higher regulatory quality predicts stronger infrastructure-maintenance and access proxies than universal underpricing.
Falsification criterion — what would disprove this
This hypothesis is considered falsified if:
SUPPORTED if the treatment coefficient has the pre-registered sign at p<0.10. REFUTED if the opposite sign is significant at p<0.10. Otherwise PARTIAL.
formal test & threshold
test: panel_fe_infrastructure_user_pricing_quality threshold: [object Object]
Method
- Template
panel_fe- Fixed effects
country, year- Clustering
country- Sample
- 40 countries · 1996 – 2023
- Evidence type
- associational
Local-data first-pass TWFE screen; upgrade to exact treatment/outcome datasets before scoreboard promotion.
Data
| Variable | Source | Transform |
|---|---|---|
qol_or_prosperity_outcome outcome | world_bank_wdi:EG.ELC.ACCS.ZStier 2 | level_or_growth_proxy |
market_or_intervention_proxy treatment | wgi:RQ.ESTtier 4 | level |
log_gdp_pc control | world_bank_wdi:NY.GDP.PCAP.KDtier 2 | log |
rule_of_law control | wgi:RL.ESTtier 4 | level |
● ready · ● pending · ● reconstruct-needed
Detailed result card
Result card — infrastructure_user_pricing_quality
Verdict: PARTIAL — coef=-4.116, p=0.289 (above α=0.1); direction inconclusive
Pre-registration
- Claim: Higher regulatory quality predicts stronger infrastructure-maintenance and access proxies than universal underpricing.
- Falsification rule: SUPPORTED if the treatment coefficient has the pre-registered sign at p<0.10. REFUTED if the opposite sign is significant at p<0.10. Otherwise PARTIAL.
- Falsification test: panel_fe_infrastructure_user_pricing_quality
Estimate
- Method: linearmodels.PanelOLS
- Coefficient (treatment): -4.116
- Std error: 3.878
- p-value: 0.289
- Observations: 795, countries: 32
- Within R²: 0.371
- Fixed effects: entity=True, time=True
- Clustering: country
Variables resolved
world_bank_wdi:EG.ELC.ACCS.ZS→ qol_or_prosperity_outcome (outcome, publisher=world_bank_wdi, n=7746)wgi:RQ.EST→ market_or_intervention_proxy (treatment, publisher=wgi, n=5169)world_bank_wdi:NY.GDP.PCAP.KD→ log_gdp_pc (controls, publisher=world_bank_wdi, n=12104)wgi:RL.EST→ rule_of_law (controls, publisher=wgi, n=5296)
Generated by scripts/run_panel_fe.py at 2026-06-29T17:52:08+00:00
Strongest opposing argument
Every hypothesis ships with its charitable opposing argument. The framework earns credibility by handling objections at their strongest, not weakest.