# Verification checks (P4)

• Clean re-run of analysis.py: results.json byte-identical (cmp) -> PASS
• n_sub1+n_sub2==n_analysed==240 -> PASS
• exclusions sum: 319-sum(removed)==240 -> PASS
• effect_se>0 -> PASS
• CI contains estimate -> PASS
• CI symmetric 1.96*se -> PASS
• model_metric<baseline_metric -> PASS
• R2 identity 1-(model/baseline)^2 -> PASS
• sample_end<=2019-10-01 and start<end -> PASS
• chow p consistent with stability_conclusion -> PASS
• conclusion consistent with CI -> PASS
• table1 matches results -> PASS
• magnitude plausible (Okun beta ~ -0.2..-0.5 in literature-scale) -> PASS
• chow df == (2,236) -> PASS