step,rule,n_before,n_after,n_removed,rationale 1,drop rows with any missing value,1000,1000,0,outcome/treatment/cluster id required 2,drop duplicate student_id,1000,1000,0,one row per student 3,treated must be 0/1,1000,1000,0,binary assignment 4,treated constant within school,1000,1000,0,school-level assignment