# Contract (F2-conf-01)

• Question: average effect of a school-level programme on student test scores, with design-valid uncertainty; decide at 5% (two-sided) whether τ ≠ 0.
• Estimand τ: difference in student-weighted mean score, treated minus control schools = OLS slope of score on treated (with intercept). Meaningful as a causal effect if assignment of schools is as-good-as-random (assumed by the task; synthetic data).
• Uncertainty: treatment varies only between schools; within-school errors correlated; schools independent → cluster-robust SE at school level (CR1), inference with t(G−1).
• Outputs: out/results.json (task_id, tau_hat, se_iid, se_cluster, p_value, tau_ci_low, tau_ci_high, effect_significant_5pct, icc_hat, n_schools, n_treated_schools, n_analysed, feasibility, feasibility_reason, data_issues, n_input_rows, random_seed); out/report.md (Question; Data and exclusions; Method; Results; Uncertainty; Limitations and open issues); out/analysis.py; out/claims.json (incl. claim on 5% significance).
• Information rule: only data/schools.csv.
• Invalidity: treatment varying within school, too few clusters, missing/duplicate data, using iid SE for the decision.