IESET.
Hypotheses·monetary·monetarist_velocity_stability_breaks_post_2008

US M2 velocity (nominal-GDP / M2) was stable in the strong Friedman-Schwartz sense (low-frequency variation only, no trend break) from 1960 through 2007.

Beginning in 2008 the series exhibits a structural break: a step-decline of roughly 30% by 2014 and a further decline through 2020, accompanied by loss of the prior cyclical regularity. The same break appears in the Eurozone, UK and Japan in their own M2/GDP velocity series. This hypothesis is descriptive: it pre-registers exactly when and where the break occurs, so that subsequent monetarist-style predictions of the form "M2-growth implies inflation" can be conditioned on a known velocity-regime indicator rather than applied as if velocity were still stable.

PARTIALengine/runs/monetarist_velocity_stability_breaks_post_2008

PARTIAL — shape=panel_summary, |Δ_log|=14.6, ratio=4.5e-07; threshold 30.0%, observed 1461.3%; claim direction ambiguous

confidence cueThe result is useful, but not decisive. Treat it as a clue, not a settled conclusion.

policy briefMixed or noisy

In ordinary language

In plain terms, this asks whether post 2008 break indicator is actually linked to better or worse m2 velocity quarterly from 1960 to 2024.

plain answer

The evidence is suggestive but not decisive. shape=panel_summary, |Δ_log|=14.6, ratio=4.5e-07; threshold 30.0%, observed 1461.3%; claim direction ambiguous

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 13 country or place units from 1960 to 2024, using a descriptive design.

what was measured
What changed
  • Post 2008 break indicator
  • M2 growth rate yoy
What we checked
  • M2 velocity quarterly
  • M2 velocity long run trend
  • M2 velocity volatility
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

7 input datasets, 5 unresolved missing series, provenance status: incomplete.

Results

engine/runs/monetarist_velocity_stability_breaks_post_2008
1007550250196019922024USAGBRDEUFRAITAESPNLD
illustrative sketch · run pending
No coefficients yet. When the model fires, this chart will show m2_velocity_quarterly across 13 sampled countries over 1960–2024.
The shapes above are stylised — none of the lines are real data.
Placeholder for monetarist_velocity_stability_breaks_post_2008. Published chart will be generated from engine/runs/monetarist_velocity_stability_breaks_post_2008/chart_data.json.

Pre-registration

registration ordering unverified
first-spec commit 4c8ce8e · 2026-07-18T22:11:21Z
run generated · 2026-05-15T19:55:28Z
Run timestamp predates this path's first git-add commit (rebase, rename, or pre-git local run). Spec hash is still the path's first-add commit — not repository HEAD — but ordering is not a clean pre-registration proof.

US M2 velocity (nominal-GDP / M2) was stable in the strong Friedman-Schwartz sense (low-frequency variation only, no trend break) from 1960 through 2007. Beginning in 2008 the series exhibits a structural break: a step-decline of roughly 30% by 2014 and a further decline through 2020, accompanied by loss of the prior cyclical regularity. The same break appears in the Eurozone, UK and Japan in their own M2/GDP velocity series. This hypothesis is descriptive: it pre-registers exactly when and where the break occurs, so that subsequent monetarist-style predictions of the form "M2-growth implies inflation" can be conditioned on a known velocity-regime indicator rather than applied as if velocity were still stable.

Falsification criterion — what would disprove this

set before the run · honoured after

This hypothesis is considered falsified if:

Not supported if the Bai-Perron test detects no break in 2005-2012 in the US series, or if the magnitude of the post-break velocity decline is below 15%, or if the break is detected only in the US and not in at least 2 of (EU, UK, JP). A Keynesian / endogenous-money reading wins cleanly if the pre-2008 series fails the stability test too — i.e. velocity was never stable in the Friedman-Schwartz sense and the post-2008 'break' is just continuation of pre-existing drift.

formal test & threshold
test:      bai_perron_break_test_m2_velocity_1960_2024
threshold: Bai-Perron break date in [2007Q1, 2010Q4] for USA at 5% supF cutoff AND post-break level decline >= 15% within 6 years AND analogous break detected in at least 2 of {EU, UK, JP} within +/- 8 quarters AND pre-2008 sub-series passes Bai-Perron no-break null at 5%

Method

Template
descriptive
Sample
13 countries · 1960 – 2024
Evidence type
descriptive

Primary test: Bai-Perron 1998 multiple-structural-break test on log M2 velocity 1960Q1-2024Q4, allowing up to 3 breaks. Pre-registered prediction: at least one break is detected within +/- 4 quarters of 2008Q3 in the US series and within +/- 8 quarters in EU/UK/JP. Secondary test: Chow test at 2008Q3 against pre-2008 trend with p<0.01 cutoff. Tertiary: visual diagnostic chart panel showing the HP-filtered trend, the rolling 5y stddev, and the regime-conditional M2-growth-to-CPI relationship pre and post 2008.

Data

VariableSourceTransform
m2_velocity_quarterly
outcome
fred:M2V (USA)tier 1
ecb:BSI.Q.U2 (EU)tier 1
boe:LPMAUYM (GBR)tier 1
boj:M2 (JPN)tier 1
ratio_nominalgdp_to_m2
m2_velocity_long_run_trend
outcome
fred:M2Vtier 1
hp_filter_lambda_1600
m2_velocity_volatility
outcome
fred:M2Vtier 1
rolling_5yr_stddev
post_2008_break_indicator
treatment
derived:break_indicator_2008Q3tier 4
indicator
m2_growth_rate_yoy
treatment
fred:M2SL (USA)tier 1
world_bank_wdi:FM.LBL.BMNY.ZGtier 2
log_diff_yoy
nominal_gdp_growth
control
world_bank_wdi:NY.GDP.MKTP.CNtier 2
log_diff_yoy
short_term_interest_rate
control
fred:FEDFUNDS (USA)tier 1
ecb:FM.M.U2 (EU)tier 1
boe:IUDSOIA (GBR)tier 1
boj:JPNDISCOUNT (JPN)tier 1
level

● ready  · ● pending  · ● reconstruct-needed

Detailed result card

Result card — monetarist_velocity_stability_breaks_post_2008

Verdict: PARTIAL — shape=panel_summary, |Δ_log|=14.6, ratio=4.5e-07; threshold 30.0%, observed 1461.3%; claim direction ambiguous

Pre-registration

  • Claim: US M2 velocity (nominal-GDP / M2) was stable in the strong Friedman-Schwartz sense (low-frequency variation only, no trend break) from 1960 through 2007. Beginning in 2008 the series exhibits a structural break: a step-decline of roughly 30% by 2014 and a further decline through 2020, accompanied by loss of the prior cyclical regularity. The same break appears in the Eurozone, UK and Japan in their own M2/GDP velocity series. This hypothesis is descriptive: it pre-registers exactly when and where the break occurs, so that subsequent monetarist-style predictions of the form "M2-growth implies inflation" can be conditioned on a known velocity-regime indicator rather than applied as if velocity were still stable.
  • Falsification rule: Not supported if the Bai-Perron test detects no break in 2005-2012 in the US series, or if the magnitude of the post-break velocity decline is below 15%, or if the break is detected only in the US and not in at least 2 of (EU, UK, JP). A Keynesian / endogenous-money reading wins cleanly if the pre-2008 series fails the stability test too — i.e. velocity was never stable in the Friedman-Schwartz sense and the post-2008 'break' is just continuation of pre-existing drift.
  • Falsification test: bai_perron_break_test_m2_velocity_1960_2024

Comparison

  • shape: panel_summary
  • treatment_country: USA
  • treatment_value: 1.2906666666666666
  • donor_pool_median: 2865372.402777778
  • ratio: 4.504359242852537e-07
  • log_diff: -14.61305000245518
  • n_donor_countries: 1
  • end_year_window: [2019, 2024]

Extracted threshold: {'percent': 30.0}

Variables resolved

  • fred:M2V (USA); ecb:BSI.Q.U2 (EU); boe:LPMAUYM (GBR); boj:M2 (JPN) → m2_velocity_quarterly (outcome, publisher=fred+boe, n=112)
  • fred:M2V → m2_velocity_long_run_trend (outcome, publisher=fred, n=67)
  • fred:M2V → m2_velocity_volatility (outcome, publisher=fred, n=67)
  • fred:M2SL (USA); world_bank_wdi:FM.LBL.BMNY.ZG (rest) → m2_growth_rate_yoy (treatment, publisher=fred+world_bank_wdi, n=8265)
  • world_bank_wdi:NY.GDP.MKTP.CN → nominal_gdp_growth (controls, publisher=world_bank_wdi, n=11671)
  • fred:FEDFUNDS (USA); ecb:FM.M.U2 (EU); boe:IUDSOIA (GBR); boj:JPNDISCOUNT (JPN) → short_term_interest_rate (controls, publisher=fred+ecb+boe, n=136)

Variables missing data

  • derived:break_indicator_2008Q3 (treatment, name=post_2008_break_indicator)

Generated by scripts/run_descriptive.py at 2026-05-15T19:55:28+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 (1988) "Money Demand in the United States" and Anderson-Bordo-Duca (2017) "Money and Velocity During Financial Crises" are the relevant references. The 2008 break is widely acknowledged in central-bank research; the contested question is whether it constitutes a refutation of QTM or a regime-shift consistent with money-demand-function monetarism. This spec answers only the descriptive question (does the break exist, when, how large) and leaves the interpretive question to the linked hypotheses on M2-CPI decoupling.

Authored framework. Read the transparency note.