{
  "benchmark": "Causal Forge",
  "replications": 100,
  "samples_per_replication": 3000,
  "cross_fitting_folds": 5,
  "structural_truth": "known heterogeneous individual treatment effects",
  "summary": {
    "both_correct": {
      "naive": {
        "mean_estimate": 3.1123144027184075,
        "bias": 1.110939263534936,
        "mean_absolute_error": 1.110939263534936,
        "rmse": 1.1132682867094192
      },
      "ipw": {
        "mean_estimate": 2.005159416540855,
        "bias": 0.0037842773573832744,
        "mean_absolute_error": 0.0643549025548575,
        "rmse": 0.07985124612336089
      },
      "outcome_regression": {
        "mean_estimate": 2.0031127881794304,
        "bias": 0.0017376489959579633,
        "mean_absolute_error": 0.038795035337436425,
        "rmse": 0.04801133697032812
      },
      "aipw": {
        "mean_estimate": 2.0017294974257873,
        "bias": 0.00035435824231527135,
        "mean_absolute_error": 0.04261334125461211,
        "rmse": 0.05444966094807796,
        "confidence_interval_coverage": 0.89
      }
    },
    "propensity_misspecified": {
      "naive": {
        "mean_estimate": 3.1123144027184075,
        "bias": 1.110939263534936,
        "mean_absolute_error": 1.110939263534936,
        "rmse": 1.1132682867094192
      },
      "ipw": {
        "mean_estimate": 2.1339948243616265,
        "bias": 0.13261968517815434,
        "mean_absolute_error": 0.1341636821632256,
        "rmse": 0.14885056735045618
      },
      "outcome_regression": {
        "mean_estimate": 2.0031127881794304,
        "bias": 0.0017376489959579633,
        "mean_absolute_error": 0.038795035337436425,
        "rmse": 0.04801133697032812
      },
      "aipw": {
        "mean_estimate": 2.002138366914246,
        "bias": 0.0007632277307738455,
        "mean_absolute_error": 0.04142272629021512,
        "rmse": 0.05271409176654249,
        "confidence_interval_coverage": 0.92
      }
    },
    "outcome_misspecified": {
      "naive": {
        "mean_estimate": 3.1123144027184075,
        "bias": 1.110939263534936,
        "mean_absolute_error": 1.110939263534936,
        "rmse": 1.1132682867094192
      },
      "ipw": {
        "mean_estimate": 2.005159416540855,
        "bias": 0.0037842773573832744,
        "mean_absolute_error": 0.0643549025548575,
        "rmse": 0.07985124612336089
      },
      "outcome_regression": {
        "mean_estimate": 2.2701977886081592,
        "bias": 0.26882264942468725,
        "mean_absolute_error": 0.26882264942468725,
        "rmse": 0.2753485792353652
      },
      "aipw": {
        "mean_estimate": 2.009154042503896,
        "bias": 0.007778903320424111,
        "mean_absolute_error": 0.048137374861682396,
        "rmse": 0.06166591119979539,
        "confidence_interval_coverage": 0.99
      }
    },
    "both_misspecified": {
      "naive": {
        "mean_estimate": 3.1123144027184075,
        "bias": 1.110939263534936,
        "mean_absolute_error": 1.110939263534936,
        "rmse": 1.1132682867094192
      },
      "ipw": {
        "mean_estimate": 2.1339948243616265,
        "bias": 0.13261968517815434,
        "mean_absolute_error": 0.1341636821632256,
        "rmse": 0.14885056735045618
      },
      "outcome_regression": {
        "mean_estimate": 2.2701977886081592,
        "bias": 0.26882264942468725,
        "mean_absolute_error": 0.26882264942468725,
        "rmse": 0.2753485792353652
      },
      "aipw": {
        "mean_estimate": 2.396631864687349,
        "bias": 0.395256725503877,
        "mean_absolute_error": 0.395256725503877,
        "rmse": 0.4048953844650616,
        "confidence_interval_coverage": 0.01
      }
    }
  }
}