IESET.
Hypotheses·monetary·baa_aaa_spread_real_activity_us_1919_2026

Spikes in the US Baa-Aaa corporate bond spread are followed by deteriorating real activity, visible as rising unemployment and falling industrial production within twelve months.

SUPPORTEDengine/runs/baa_aaa_spread_real_activity_us_1919_2026

supported

confidence cueThis is a clear pass for the claim as written. It still applies only to this sample, period, and method.

policy briefClear support

In ordinary language

In plain terms, this asks whether baa aaa credit spread is actually linked to better or worse unemployment rate from 1919 to 2026.

plain answer

The data clearly moved in the predicted direction. supported

why it matters

This matters because monetary 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 1919 to 2026, using a event study design.

what was measured
What changed
  • Baa aaa credit spread
What we checked
  • Unemployment rate
  • Industrial production
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

4 input datasets, 0 unresolved missing series, provenance status: reproducible hash verified.

Results

engine/runs/baa_aaa_spread_real_activity_us_1919_2026
1007550250191919732026USA
illustrative sketch · run pending
No coefficients yet. When the model fires, this chart will show unemployment_rate across 1 sampled countries over 1919–2026.
The shapes above are stylised — none of the lines are real data.
Placeholder for baa_aaa_spread_real_activity_us_1919_2026. Published chart will be generated from engine/runs/baa_aaa_spread_real_activity_us_1919_2026/chart_data.json.

Who has skin in the game — schools predicting on this

1 school list this hypothesis as a test of their position. The chips below are school-level scoreboard outcomes, not a second hypothesis verdict.

hypothesis verdict vs scoreboard outcome

The banner verdict judges this hypothesis as written. The scoreboard asks whether each school's polarity-corrected prediction was right. Raw status is not a school win: SUPPORTED supports schools that needed SUPPORTED, but refutes schools that needed REFUTED.

New Keynesian (mainstream synthesis)wins if SUPPORTEDschool supported

Pre-registration

pre-registered
first-spec commit 4c8ce8e · 2026-07-18T22:11:21Z

Spikes in the US Baa-Aaa corporate bond spread are followed by deteriorating real activity, visible as rising unemployment and falling industrial production within twelve months.

Falsification criterion — what would disprove this

set before the run · honoured after

This hypothesis is considered falsified if:

Identify non-overlapping months where the Baa-Aaa spread is at least 1.0 percentage point above its trailing 24-month median. A completed episode supports the claim if unemployment rises at least +0.50pp OR industrial production falls at least 3% within the following 12 months. SUPPORTED if at least 65% of completed episodes pass and the median unemployment change is positive. REFUTED if fewer than 45% pass or median unemployment change is <= 0 and median industrial-production change is >= 0. PARTIAL otherwise.

formal test & threshold
test:      fred_baa_aaa_spread_real_activity_12m
threshold: SUPPORTED: pass rate >= 65% and median unemployment change > 0pp; REFUTED: pass rate < 45% or both median unemployment change <= 0 and median IP change >= 0.

Method

Template
event_study
Clustering
none
Sample
1 countries · 1919 – 2026
Evidence type
associational

Monthly event-window checklist over long-run FRED spread and real-activity series.

Data

VariableSourceTransform
unemployment_rate
outcome
fred:UNRATEtier 1
max 12-month forward level minus episode-month level
industrial_production
outcome
fred:INDPROtier 1
minimum 12-month forward log change from episode month
baa_aaa_credit_spread
treatment
fred:BAAtier 1
fred:AAAtier 1
Baa seasoned corporate yield minus Aaa seasoned corporate yield

● ready  · ● pending  · ● reconstruct-needed

Detailed result card

Result card - baa_aaa_spread_real_activity_us_1919_2026

Verdict: supported - 6/6 episodes pass; median max unemployment change 0.90pp; median min IP change -7.4%

A pass means unemployment rises at least +0.50pp or industrial production falls at least 3% within 12 months of a Baa-Aaa spread spike.

Strongest opposing argument

Every hypothesis ships with its charitable opposing argument. The framework earns credibility by handling objections at their strongest, not weakest.

Notes

Long FRED history allows a stress-window test rather than relying on the short high-yield OAS vintage available on disk.

Authored framework. Read the transparency note.