IESET.
Hypotheses·monetary·lucas_critique_pre_post_volcker_phillips_curve_shift

The estimated reduced-form parameters of the US Phillips curve (slope on unemployment-NAIRU gap; coefficient on lagged inflation) shifted significantly between the pre-Volcker (1960Q1-1979Q3) and post-Volcker (1985Q1-2019Q4) regimes.

The pre-registered prediction is that the Phillips slope flattened in absolute magnitude (from above 0.4 to below 0.2) AND the lagged-inflation coefficient fell (from above 0.85 to below 0.6). The hypothesis is the empirical embodiment of Lucas's (1976) critique: when monetary regime shifts, agents re-optimise expectation formation, and the reduced-form Phillips parameters that appear stable within a regime are not stable across regimes.

SUPPORTEDengine/runs/lucas_critique_pre_post_volcker_phillips_curve_shift

SUPPORTED — coef=-0.01825 (sign matches claim -), p=0.00156

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

policy briefNeeds review

In ordinary language

In plain terms, this asks whether post volcker regime indicator is actually linked to better or worse cpi inflation quarterly from 1960 to 2024.

plain answer

The data clearly moved in the predicted direction. coef=-0.01825 (sign matches claim -), p=0.00156

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 1960 to 2024, using a panel fe design.

what was measured
What changed
  • Post volcker regime indicator
  • Unemployment minus nairu gap
What we checked
  • Cpi inflation quarterly
  • Phillips slope estimate
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/lucas_critique_pre_post_volcker_phillips_curve_shift
1007550250196019922024USA
illustrative sketch · run pending
No coefficients yet. When the model fires, this chart will show cpi_inflation_quarterly across 1 sampled countries over 1960–2024.
The shapes above are stylised — none of the lines are real data.
Placeholder for lucas_critique_pre_post_volcker_phillips_curve_shift. Published chart will be generated from engine/runs/lucas_critique_pre_post_volcker_phillips_curve_shift/chart_data.json.

Pre-registration

pre-registered
first-spec commit 098ce96 · 2026-04-30T12:57:33Z
run generated · 2026-06-29T17:54:21Z

The estimated reduced-form parameters of the US Phillips curve (slope on unemployment-NAIRU gap; coefficient on lagged inflation) shifted significantly between the pre-Volcker (1960Q1-1979Q3) and post-Volcker (1985Q1-2019Q4) regimes. The pre-registered prediction is that the Phillips slope flattened in absolute magnitude (from above 0.4 to below 0.2) AND the lagged-inflation coefficient fell (from above 0.85 to below 0.6). The hypothesis is the empirical embodiment of Lucas's (1976) critique: when monetary regime shifts, agents re-optimise expectation formation, and the reduced-form Phillips parameters that appear stable within a regime are not stable across regimes.

Falsification criterion — what would disprove this

set before the run · honoured after

This hypothesis is considered falsified if:

Not supported if (a) the pre-Volcker Phillips slope is below 0.3 in absolute magnitude, OR (b) the post-Volcker slope is above 0.25 in absolute magnitude, OR (c) the Wald test of equality of slopes does not reject at p<0.05, OR (d) the Bai-Perron break test fails to detect a break in 1979-1984. A neo-Keynesian "stable Phillips curve" reading wins cleanly if Wald test fails to reject equality across regimes. A pure-supply-shock reading wins if including richer oil and import controls eliminates the coefficient differences.

formal test & threshold
test:      subsample_phillips_estimation_with_break_test
threshold: pre_volcker_slope >= 0.4 in absolute magnitude AND post_volcker_slope <= 0.2 in absolute magnitude AND Wald test of slope equality rejects at p<0.05 AND Bai-Perron break detected in [1979Q4, 1984Q4] AND lagged-inflation coefficient: pre-Volcker >= 0.85, post-Volcker <= 0.6

Method

Template
panel_fe
Fixed effects
Clustering
newey_west_4_lags
Sample
1 countries · 1960 – 2024
Evidence type
associational

Two pre-registered tests. Test 1: estimate Phillips equations separately on 1960Q1-1979Q3 and 1985Q1-2019Q4 sub-samples with identical specifications (lagged inflation, unemployment gap, oil shocks, import shocks); compare slope and lagged-inflation coefficients with bootstrap CIs and Wald test of equality. Test 2: Bai-Perron multiple-break test on rolling 60Q Phillips slope estimate 1960-2024. Pre-registered prediction: at least one structural break detected in the 1979-1984 window. Robustness: Cogley-Sargent (2005) Bayesian time-varying-parameter VAR replication.

Data

VariableSourceTransform
cpi_inflation_quarterly
outcome
fred:CPIAUCSLtier 1
log_diff_qoq_annualised
phillips_slope_estimate
outcome
derived:phillips_slope_rolling_windowtier 4
rolling_60q_ols_coefficient
post_volcker_regime_indicator
treatment
derived:volcker_regime_break_1985Q1tier 4
indicator
unemployment_minus_nairu_gap
treatment
fred:UNRATEtier 1
fred:NROUtier 1
difference
lagged_cpi_inflation
treatment
fred:CPIAUCSLtier 1
lag_4q_log_diff_yoy
oil_price_change
control
fred:WTISPLCtier 1
log_diff_qoq
import_price_change
control
fred:IRtier 1
log_diff_qoq
ten_year_inflation_expectations
control
fred:T10YIEtier 1
level

● ready  · ● pending  · ● reconstruct-needed

Detailed result card

Result card — lucas_critique_pre_post_volcker_phillips_curve_shift

Verdict: SUPPORTED — coef=-0.01825 (sign matches claim -), p=0.00156

Pre-registration

  • Claim: The estimated reduced-form parameters of the US Phillips curve (slope on unemployment-NAIRU gap; coefficient on lagged inflation) shifted significantly between the pre-Volcker (1960Q1-1979Q3) and post-Volcker (1985Q1-2019Q4) regimes. The pre-registered prediction is that the Phillips slope flattened in absolute magnitude (from above 0.4 to below 0.2) AND the lagged-inflation coefficient fell (from above 0.85 to below 0.6). The hypothesis is the empirical embodiment of Lucas's (1976) critique: when monetary regime shifts, agents re-optimise expectation formation, and the reduced-form Phillips parameters that appear stable within a regime are not stable across regimes.
  • Falsification rule: Not supported if (a) the pre-Volcker Phillips slope is below 0.3 in absolute magnitude, OR (b) the post-Volcker slope is above 0.25 in absolute magnitude, OR (c) the Wald test of equality of slopes does not reject at p<0.05, OR (d) the Bai-Perron break test fails to detect a break in 1979-1984. A neo-Keynesian "stable Phillips curve" reading wins cleanly if Wald test fails to reject equality across regimes. A pure-supply-shock reading wins if including richer oil and import controls eliminates the coefficient differences.
  • Falsification test: subsample_phillips_estimation_with_break_test

Estimate

  • Method: statsmodels OLS time-series fallback
  • Coefficient (treatment): -0.01825
  • Std error: 0.005769
  • p-value: 0.00156
  • Observations: 22, countries: 1
  • Within R²: 0.898
  • Fixed effects: entity=False, time=False
  • Clustering: HAC(maxlags=4)

Variables resolved

  • fred:CPIAUCSL → cpi_inflation_quarterly (outcome, publisher=fred, n=80)
  • fred:UNRATE; fred:NROU → unemployment_minus_nairu_gap (treatment, publisher=fred, n=79)
  • fred:CPIAUCSL → lagged_cpi_inflation (treatment, publisher=fred, n=80)
  • fred:WTISPLC → oil_price_change (controls, publisher=fred, n=81)
  • fred:IR → import_price_change (controls, publisher=fred, n=45)
  • fred:T10YIE → ten_year_inflation_expectations (controls, publisher=fred, n=24)

Variables missing data

  • derived:phillips_slope_rolling_window (outcome, name=phillips_slope_estimate) — vintage not on disk
  • derived:volcker_regime_break_1985Q1 (treatment, name=post_volcker_regime_indicator) — vintage not on disk

Generated by scripts/run_panel_fe.py at 2026-06-29T17:54:21+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.

Notes

Lucas (1976 Carnegie-Rochester) is the foundational reference; Cogley- Sargent (2005), Stock-Watson (2007), Ball-Mazumder (2011) on Phillips curve flattening are the primary modern empirics. The hypothesis is conceptually adjacent to lucas_expectations_anchoring_post_volcker but tests a different parameter (Phillips slope and lagged-inflation coefficient, vs AR persistence in inflation). Both should move together if the canonical Lucas-Volcker story is correct.

Authored framework. Read the transparency note.