1[2 {"id":"C1","text":"The classical one-way ANOVA does not reject equal mean daily changes across the five weekdays (F=0.263, p=0.90).","results_keys":["anova_f_stat","anova_p_value","n_analysed"],"status":"supported","caveat":"Equal-variance assumption is violated (Levene p~1e-7); serial dependence ignored."},3 {"id":"C2","text":"The Monday contrast is +0.050 bp with 95% Welch CI [-0.319, 0.420] bp, which contains zero.","results_keys":["effect_estimate","effect_ci_low","effect_ci_high","supp_effect_se","supp_effect_welch_p"],"status":"supported","caveat":"Assumes independent daily changes; effects below ~0.4 bp cannot be excluded."},4 {"id":"C3","text":"Weekday-specific means estimated on 2000-2009 do not improve on the zero-change forecast over 2010-2019 (RMSE 4.884 vs 4.876 bp).","results_keys":["model_metric","baseline_metric","supp_rmse_ratio_model_over_baseline","n_train","n_test"],"status":"supported","caveat":"No formal forecast-comparison test; single fixed split."},5 {"id":"C4","text":"Overall conclusion: no detectable day-of-week effect in daily changes of the 10-year Treasury yield, 2000-2019.","results_keys":["conclusion","anova_p_value"],"status":"supported","caveat":"Non-rejection, not proof of zero effect."},6 {"id":"C5","text":"A rank-based Kruskal-Wallis test also does not reject equal weekday distributions.","results_keys":["supp_kruskal_p"],"status":"supported","caveat":"Robustness check only."}7]8