IESET.
Hypotheses·financial stability·credit_gap_unemployment_spike

A widening credit gap is associated with subsequent increases in unemployment.

REFUTEDengine/runs/credit_gap_unemployment_spike

REFUTED — coef=-0.02233 (sign opposite claim +), p=0.0548

confidence cueThis test cuts against the claim as written or misses its pre-declared threshold.

policy briefNeeds review

In ordinary language

In plain terms, this asks whether WS CREDIT GAP is actually linked to better or worse SL.UEM.TOTL.ZS from 1995 to 2023.

plain answer

The data did not support the prediction. coef=-0.02233 (sign opposite claim +), p=0.0548

why it matters

This matters because financial stability claims should change belief only when they survive a pre-declared empirical test.

how the test works

It compares 1 country or place units from 1995 to 2023, using a panel fe design, with fixed effects for country and year.

what was measured
What changed
  • WS CREDIT GAP
What we checked
  • SL.UEM.TOTL.ZS
what this does not prove

A single test is not the whole truth. It narrows the claim under a specific sample, time period, and method. Strong policy conclusions need the pattern to survive nearby tests, alternative data, and serious objections.

verification

No evidence packet has been generated yet.

Results

engine/runs/credit_gap_unemployment_spike
1007550250199520092023GLOBAL
illustrative sketch · run pending
No coefficients yet. When the model fires, this chart will show SL.UEM.TOTL.ZS across 1 sampled countries over 1995–2023.
The shapes above are stylised — none of the lines are real data.
Placeholder for credit_gap_unemployment_spike. Published chart will be generated from engine/runs/credit_gap_unemployment_spike/chart_data.json.

Pre-registration

pre-registered
first-spec commit bea2d5c · 2026-06-30T18:46:55Z
run generated · 2026-06-30T14:46:14Z

A widening credit gap is associated with subsequent increases in unemployment.

Falsification criterion — what would disprove this

set before the run · honoured after

This hypothesis is considered falsified if:

SUPPORTED if the primary treatment coefficient has the pre-registered + sign at p<=0.10 with minimum 12 countries and 180 observations. REFUTED if opposite sign at p<=0.10. Otherwise PARTIAL.

formal test & threshold
test:      panel_fe_credit_gap_unemployment_spike
threshold: [object Object]

Method

Template
panel_fe
Fixed effects
country, year
Clustering
country
Sample
1 countries · 1995 – 2023
Evidence type
associational

Data

VariableSourceTransform
SL.UEM.TOTL.ZS
outcome
world_bank_wdi:SL.UEM.TOTL.ZStier 2
level
WS_CREDIT_GAP
treatment
bis:WS_CREDIT_GAPtier 2
level
WS_DSR
control
bis:WS_DSRtier 2
level
NY.GDP.PCAP.KD
control
world_bank_wdi:NY.GDP.PCAP.KDtier 2
log
NE.TRD.GNFS.ZS
control
world_bank_wdi:NE.TRD.GNFS.ZStier 2
level

● ready  · ● pending  · ● reconstruct-needed

Detailed result card

Result card — credit_gap_unemployment_spike

Verdict: REFUTED — coef=-0.02233 (sign opposite claim +), p=0.0548

Pre-registration

  • Claim: A widening credit gap is associated with subsequent increases in unemployment.
  • Falsification rule: SUPPORTED if the primary treatment coefficient has the pre-registered + sign at p<=0.10 with minimum 12 countries and 180 observations. REFUTED if opposite sign at p<=0.10. Otherwise PARTIAL.
  • Falsification test: panel_fe_credit_gap_unemployment_spike

Estimate

  • Method: linearmodels.PanelOLS
  • Coefficient (treatment): -0.02233
  • Std error: 0.0116
  • p-value: 0.0548
  • Observations: 605, countries: 25
  • Within R²: 0.128
  • Fixed effects: entity=True, time=True
  • Clustering: country

Variables resolved

  • world_bank_wdi:SL.UEM.TOTL.ZS → SL.UEM.TOTL.ZS (outcome, publisher=world_bank_wdi, n=6874)
  • bis:WS_CREDIT_GAP → WS_CREDIT_GAP (treatment, publisher=bis, n=1914)
  • bis:WS_DSR → WS_DSR (controls, publisher=bis, n=861)
  • world_bank_wdi:NY.GDP.PCAP.KD → NY.GDP.PCAP.KD (controls, publisher=world_bank_wdi, n=12104)
  • world_bank_wdi:NE.TRD.GNFS.ZS → NE.TRD.GNFS.ZS (controls, publisher=world_bank_wdi, n=10714)

Generated by scripts/run_panel_fe.py at 2026-06-30T14:46:14+00:00

Authored framework. Read the transparency note.