1# Verification checks (P4)23| check | outcome |4|---|---|5| Clean re-run (deleted results.json, forecasts.csv; re-ran analysis.py) gives byte-identical files | PASS |6| forecasts.csv has 240 rows, 40 per (model, horizon) | PASS |7| target_date = origin_date + h quarters for every row | PASS |8| `actual` equals infl_annualised at target_date | PASS |9| snaive forecast equals infl_annualised at target − 4 quarters, and that date ≤ origin | PASS |10| Estimation sample at each origin ends exactly at the origin (assert in code: hist.index.max() == t) | PASS |11| RMSE ≥ MAE for all model/horizon pairs | PASS |12| rel_improvement = 1 − rmse_model/rmse_snaive (|diff| < 1e-12) | PASS |13| loss_diff_mean_h4 = rmse_snaive_h4² − rmse_model_h4² (2.81795 both) | PASS |14| dm_stat_h4 = mean/se; se > 0; hac_lags_h4 = 3 ≥ h−1 | PASS |15| HAC SE cross-checked against statsmodels OLS-on-constant HAC (Bartlett, maxlags=3, no small-sample correction): 2.086237 vs 2.086237 | PASS |16| first_origin < last_origin; n_origins = 40 | PASS |17| Exclusion ledger: 127 − 1 = 126 analysable quarters; last estimation sample 1995Q2–2025Q3 = 122 quarters, minus p=1 lag = 121 = n_analysed | PASS |18| Magnitudes: model RMSE (2.19–2.46) below snaive RMSE (≈2.85–2.88) and of the same order as the series sd (2.39) | plausible |19| Sensitivity note: HAC SE decreases with longer Bartlett lags (L=4: 1.85, L=6: 1.38) — negative higher-order autocorrelations in d_t; primary lag L=3 was fixed before seeing results | reported, not a failure |20