IESET.
Hypotheses·monetary·bis_reer_appreciation_reversal_panel

Large real effective exchange-rate appreciations mean-revert.

In the BIS real broad EER panel, a 15 percent or larger three-year REER appreciation should predict subsequent two-year real depreciation or at least materially weaker REER growth.

PARTIALengine/runs/bis_reer_appreciation_reversal_panel

PARTIAL — coef=+0.5, p=0; claim direction not auto-inferred

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 large reer appreciation is actually linked to better or worse fwd reer growth 8q from 1994 to 2026.

plain answer

The evidence is suggestive but not decisive. coef=+0.5, p=0; claim direction not auto-inferred

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 21 country or place units from 1994 to 2026, using a panel fe design, with fixed effects for country and year.

what was measured
What changed
  • Large reer appreciation
What we checked
  • Fwd reer growth 8q
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/bis_reer_appreciation_reversal_panel
1007550250199420102026USAGBRCANAUSJPNKORFRA
illustrative sketch · run pending
No coefficients yet. When the model fires, this chart will show fwd_reer_growth_8q across 21 sampled countries over 1994–2026.
The shapes above are stylised — none of the lines are real data.
Placeholder for bis_reer_appreciation_reversal_panel. Published chart will be generated from engine/runs/bis_reer_appreciation_reversal_panel/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.

Classical Liberalwins if SUPPORTEDpartial/no-call

Pre-registration

pre-registered
first-spec commit c86e9cf · 2026-05-02T16:36:30Z
run generated · 2026-06-29T17:54:10Z

Large real effective exchange-rate appreciations mean-revert. In the BIS real broad EER panel, a 15 percent or larger three-year REER appreciation should predict subsequent two-year real depreciation or at least materially weaker REER growth.

Falsification criterion — what would disprove this

set before the run · honoured after

This hypothesis is considered falsified if:

Falsified if large three-year REER appreciations do not predict weaker subsequent two-year REER growth after fixed effects, or if the raw appreciation contrast is not economically negative.

formal test & threshold
test:      bis_reer_appreciation_reversal_panel
threshold: Supported only if coefficient(large_reer_appreciation) <= -2.0 percentage points with cluster-robust p <= 0.05, raw high-minus-normal mean outcome <= -2.0 percentage points, at least 1200 observations, and at least 25 countries. Partial if exactly one of the regression or raw contrast gates clears.

Method

Template
panel_fe
Fixed effects
country, year
Clustering
country
Sample
21 countries · 1994 – 2026
Evidence type
associational

Data

VariableSourceTransform
fwd_reer_growth_8q
outcome
bis:WS_EERtier 2
100 * log(real_broad_reer_t+8 / real_broad_reer_t)
large_reer_appreciation
treatment
bis:WS_EERtier 2
indicator(12-quarter log REER growth >= 15 percent)
reer_appreciation_12q
control
bis:WS_EERtier 2
100 * log(real_broad_reer_t / real_broad_reer_t-12)

● ready  · ● pending  · ● reconstruct-needed

Detailed result card

Result card — bis_reer_appreciation_reversal_panel

Verdict: PARTIAL — coef=+0.5, p=0; claim direction not auto-inferred

Pre-registration

  • Claim: Large real effective exchange-rate appreciations mean-revert. In the BIS real broad EER panel, a 15 percent or larger three-year REER appreciation should predict subsequent two-year real depreciation or at least materially weaker REER growth.
  • Falsification rule: Falsified if large three-year REER appreciations do not predict weaker subsequent two-year REER growth after fixed effects, or if the raw appreciation contrast is not economically negative.
  • Falsification test: bis_reer_appreciation_reversal_panel

Estimate

  • Method: statsmodels OLS FE fallback (linearmodels failed: exog does not have full column rank. If you wish to proceed with model estimation irrespective of the numerical accuracy of coefficient estimates, you can set check_rank=False.)
  • Coefficient (treatment): +0.5
  • Std error: 4.705e-16
  • p-value: 0
  • Observations: 693, countries: 21
  • Within R²: 1
  • Fixed effects: entity=True, time=True
  • Clustering: country

Variables resolved

  • bis:WS_EER → fwd_reer_growth_8q (outcome, publisher=bis, n=2112)
  • bis:WS_EER → large_reer_appreciation (treatment, publisher=bis, n=2112)
  • bis:WS_EER → reer_appreciation_12q (controls, publisher=bis, n=2112)

Generated by scripts/run_panel_fe.py at 2026-06-29T17:54:10+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

Runnable via engine/runs/bis_reer_appreciation_reversal_panel/replication.py. Uses only pinned BIS vintages already on disk.

Authored framework. Read the transparency note.