1step,rule,n_before,n_after,n_removed,rationale21,rows read,2140,2140,0,data rows in data/firm_panel.csv (header excluded)32,drop column rating_2025,2140,2140,0,"rating_2025 is known only in 2025 and was built from realised defaults through 2022 and full-sample average leverage: look-ahead/outcome leakage; column removed, no rows removed"43,drop exact duplicate rows,2140,2100,40,identical copies of the same firm-year (assembly error); first copy kept54,drop rows with missing default_next,2100,1800,300,outcome not observed (years [2022]: t+1 after the 2022 data cut); not imputed65,drop rows with missing predictors,1800,1800,0,"complete-case on leverage, cash_ratio, log_sales"7