1step,rule,n_before,n_after,n_removed,rationale21,keep regression rows with dependent quarter >= 1985-01-01 (lag needs prior quarter),314,163,151,post-1984 (Great Moderation) sample; pre-1985 volatility regime not representative of 2024-2632,"drop rows t in {2020Q2,2020Q3,2020Q4} (y_t or y_{t-1} is a COVID quarter)",163,160,3,"pandemic outliers (~-28, ~+35 pp) would dominate OLS"4