1[2 {"id": "C1", "text": "The joint ANOVA test does not reject equal mean daily DGS10 changes across weekdays (F=0.263, p=0.902).", "results_keys": ["anova_f_stat", "anova_p_value", "n_analysed"], "status": "supported", "caveat": "Classical equal-variance F-test; volatility clustering not modelled."},3 {"id": "C2", "text": "The Monday contrast is +0.050 bp with 95% Welch CI [-0.319, 0.420] bp, i.e. not distinguishable from zero.", "results_keys": ["effect_estimate", "effect_ci_low", "effect_ci_high"], "status": "supported", "caveat": "Excludes only effects larger than about 0.4 bp/day; HAC errors not used."},4 {"id": "C3", "text": "Weekday-specific means estimated on 2000-2009 do not improve out-of-sample forecasts for 2010-2019: RMSE 4.884 bp vs 4.876 bp for the zero-change forecast.", "results_keys": ["model_metric", "baseline_metric", "n_train", "n_test"], "status": "supported", "caveat": "Difference not significant by a Diebold-Mariano test (p=0.063, supplementary.dm_p_value)."},5 {"id": "C4", "text": "Overall conclusion: no detectable weekday effect.", "results_keys": ["conclusion", "anova_p_value"], "status": "supported", "caveat": "Absence of evidence within the stated power, not proof of zero effect."}6]7