step,rule,n_before,n_after,n_removed,rationale 1,drop rows with missing values,1200,1200,0,required variables must be observed 2,drop duplicate firm_id,1200,1200,0,one row per firm 3,drop training_hours < 0,1200,1188,12,hours of training per employee cannot be negative; values are invalid (likely data error). Sensitivity with them retained is reported.