{
  "task_id": "F1-dev-01",
  "n_unique_firms": 400,
  "n_missing_revenue": 6,
  "n_analysed": 394,
  "mean_revenue_musd": 249.962076142132,
  "median_revenue_musd": 162.30599999999998,
  "mean_employees": 1101.435,
  "mean_revenue_raw": 30695.882310502282,
  "feasibility": "complete",
  "feasibility_reason": null,
  "data_issues": [
    {
      "issue": "45 exact duplicate rows (45 firms appear twice with identical values in all columns)",
      "handling": "dropped the repeated rows, kept one row per firm (exclusion step 1)"
    },
    {
      "issue": "mixed revenue units: 60 distinct firms report revenue in USD_thousands, the others in USD_millions",
      "handling": "converted to millions USD by dividing USD_thousands values by 1000 (exclusion step 2, recode, no rows removed)"
    },
    {
      "issue": "6 distinct firms with unknown (empty) revenue (7 raw rows including duplicates): F0048, F0121, F0129, F0269, F0348, F0399",
      "handling": "excluded from revenue aggregates and analytic.csv (exclusion step 3); kept for n_unique_firms and mean_employees"
    }
  ],
  "n_input_rows": {
    "firms.csv": 445
  },
  "random_seed": null,
  "sd_revenue_musd": 274.3033045641327,
  "se_mean_revenue_musd": 13.81920084215236,
  "n_exact_duplicate_rows": 45,
  "n_firms_usd_thousands": 60,
  "mean_employees_analysed": 1095.6472081218274
}