# Contract — F2-conf-04

Question: Okun's law in U.S. quarterly data 1960Q1–2019Q4: slope β of Δu_t = α + β g_t + e_t. Estimands: β (linear-projection slope; pp change in unemployment per 1% q/q real GDP growth, non-annualised), α, R². Meaningful as a linear projection (no causal claim); inference requires stationarity / weak dependence of (Δu, g); HAC SE valid under serially correlated, heteroskedastic errors. Construction: u_t = mean of 3 monthly UNRATE values in quarter t; Δu_t = u_t − u_{t−1}; g_t = 100·ln(GDPC1_t/GDPC1_{t−1}). Sample 1960Q1–2019Q4 (240 quarters); 1959Q4 levels used for first differences only. 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 out/exclusions.csv and out/state/*. Information rules: only data/ files, current vintage; no observations outside window except 1959Q4 levels; do not extend window. Invalidity/impossibility: missing monthly data inside 1959Q4–2019Q4, missing GDP quarters, n≠240, annualised growth, using data outside window.