# Contract — F2-conf-04

Question. Okun's law in U.S. quarterly data: slope β in the linear projection Δu_t = α + β g_t + e_t, 1960Q1–2019Q4 (240 quarters). Variables. u_t = mean of the 3 monthly UNRATE values in quarter t (pp); Δu_t = u_t − u_{t−1}; g_t = 100·ln(GDPC1_t/GDPC1_{t−1}) (percent, q/q, NOT annualised). The 1960Q1 differences use 1959Q4 levels. Estimands. β (Okun coefficient), α, R², mean of g_t. β is a linear-projection coefficient (meaningful with no causal claim under stationarity/weak dependence of (Δu,g) and finite 4th moments). Inference: Newey–West Bartlett HAC SE, which is consistent under serial correlation and heteroskedasticity of e_t g_t given a bandwidth growing slowly with T. 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 (state/, exclusions.csv). Information rules. Only data/; current vintage as given; observations outside 1960Q1–2019Q4 used only for 1959Q4 levels; no window extension. Invalidity / impossibility. Missing monthly UNRATE or GDPC1 values in 1959Q4–2019Q4; incomplete quarters; wrong sample size (≠240); annualised growth; using post-2019 data.