# Contract — F6-conf-01

Question. Does the weekday of a trading day predict the one-day change in the 10-year Treasury CMT yield (FRED DGS10), 2000–2019? Estimands. (i) Joint equality of the 5 weekday conditional means of Δy_t (bp), classical one-way equal-variance ANOVA F(4, n−5) on all changes. (ii) Monday contrast = mean(Mon) − mean(Tue–Fri), all changes, 95% CI (choice: Welch two-sample). (iii) Out-of-sample RMSE (2010–2019 changes) of weekday means estimated on ≤2009-12-31 changes vs zero-change forecast. Meaningful under: changes roughly independent across days (ANOVA/Welch assume independence; ANOVA assumes equal variances), stable weekday effect across periods for (iii). Rules. Drop empty DGS10 rows first; Δy_t = 100(y_t − y_{t−1}) between consecutive available obs, dated t, weekday of t; first obs has no change. Train = changes dated ≤ 2009-12-31; test ≥ 2010-01-01. Weekday means for forecasting from train only. Only data/DGS10.csv. Outputs. out/results.json (keys: n_missing_rows, n_train, n_test, anova_f_stat, anova_p_value, effect_estimate, effect_ci_low, effect_ci_high, baseline_metric, model_metric, conclusion, task_id, feasibility, feasibility_reason, data_issues, n_input_rows, n_analysed, random_seed), out/figure1.png, out/table1.csv (weekday,n,mean_bp,se_bp), out/report.md (6 sections), out/analysis.py, out/claims.json. Conclusion rule. ANOVA p ≥ 0.05 → no_detectable_effect; otherwise sign from Monday CI (if CI straddles zero after ANOVA rejects, report no_detectable_effect for the Monday contrast and explain). Invalidity. Missing/unparsable file, no weekday variation, or using test info in forecasts.