# Contract (P0)
**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 = mean score of students in treated schools − mean in control schools (student-weighted; OLS slope of score on treated with intercept). Meaningful as a causal effect if assignment of schools is as-good-as-random (simulated design); as a descriptive difference regardless.
**Uncertainty:** treatment varies only between schools; students within a school share shocks; schools independent → cluster-robust SE at school level (CR1), t reference with G−1 df. Naïve iid SE reported only as a baseline.
**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 rules:** only data/schools.csv.
**Invalidity:** treated varying within school, too few clusters (e.g. <~10) for cluster asymptotics, missing/duplicate data not handled, using iid SE for inference.