# Contract (P0)

Question: Okun's law for the US: slope β in Δu_t = α + β g_t + e_t, 1960Q1–2019Q4 (240 quarters).

• u_t = mean of 3 monthly UNRATE values in quarter t (pp); Δu_t = u_t − u_{t−1}.
• g_t = 100·ln(GDPC1_t/GDPC1_{t−1}), quarterly, NOT annualised. Estimands: β (OLS linear-projection slope), α, R²; conventional OLS SE (baseline) and Newey–West Bartlett HAC SE with justified bandwidth; 95% CI from HAC SE; whether β<0 and significant at 5% (two-sided). β is meaningful as a linear projection coefficient under stationarity/weak dependence of (Δu, g); HAC SE valid under serial correlation and heteroskedasticity of e_t with bandwidth growing slowly. Outputs: out/results.json (task_id, beta_hat, alpha_hat, r_squared, se_iid, se_hac, hac_lags, beta_ci_low, beta_ci_high, okun_negative_5pct, mean_growth, first_quarter, last_quarter, 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, out/figure1.png, plus protocol files (exclusions.csv, state/*). Information rules: only data/; current vintage as given; data outside 1960Q1–2019Q4 used only for 1959Q4 levels; window not extended. Invalidity/impossibility: missing/incomplete months or quarters inside 1959Q4–2019Q4; wrong growth definition (annualised); window extended; fewer than 240 quarters.