# 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: student-weighted mean(score|treated schools) − mean(score|control schools) = OLS slope of score on treated with intercept. Meaningful as a causal effect under (assumed) random assignment of schools; inference assumes independent schools, arbitrary within-school correlation.
- 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 (6 sections), out/analysis.py, out/claims.json (incl. 5% significance claim).
- Information rule: only data/schools.csv.
- Invalidity risks: treatment varying within school, too few clusters, using iid SE for inference (would understate uncertainty).