| Clean re-run (deleted results.json/table1/figure1, re-ran) gives byte-identical results.json |
PASS |
| ANOVA F/p cross-checked with statsmodels OLS dy~C(weekday) (F=0.26347, p=0.9015) |
PASS |
| Monday contrast cross-checked with OLS on Monday dummy, HC1 SE: CI [-0.319, 0.419] vs Welch [-0.319, 0.420] |
PASS (choice-insensitive) |
| Counts: 5217 − 215 − 1 = 5001 = n_analysed = n_train + n_test (2500+2501) = sum of table1 n |
PASS |
| exclusions.csv sums: 5217 − (215+1) = 5001 |
PASS |
| CI contains estimate; all weekday SE > 0; RMSEs > 0 |
PASS |
| Chronology: max train date 2009-12-31 < min test date 2010-01-04; forecast means from train only |
PASS |
| Magnitude: model RMSE (4.884) vs baseline (4.876) bp — same order, model slightly worse |
PASS (plausible) |
| Conclusion rule: ANOVA p=0.90 ≥ 0.05 → no_detectable_effect |
PASS |