step,rule,n_before,n_after,n_removed,rationale
1,drop entity-years whose region == 'Aggregates' in wb_entities.csv,2349,1953,396,information rule: countries/economies only
2,keep analysis year 2023 (latest year with >=150 complete countries),1953,217,1736,information rule: single cross-section in analysis year
3,drop countries with gdp_pc_ppp or life_expectancy missing in analysis year,217,197,20,information rule: no imputation