{"id":"W2139491581","doi":"10.1080/00273171.2012.640600","title":"Using Ensemble-Based Methods for Directly Estimating Causal Effects: An Investigation of Tree-Based G-Computation","year":2012,"lang":"en","type":"article","venue":"Multivariate Behavioral Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":52,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Toronto","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; U.S. Public Health Service; Heart and Stroke Foundation of Canada","keywords":"Propensity score matching; Inverse probability weighting; Statistics; Observational study; Logistic regression; Random forest; Regression; Confounding; Causal inference; Regression analysis; Inverse probability; Econometrics; Mathematics; Computer science; Machine learning; Bayesian probability","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01855168,0.001160128,0.0023465,0.002385302,0.0007753023,0.001347288,0.002194534,0.001407062,0.001914767],"category_scores_gemma":[0.0788781,0.0007024013,0.001613345,0.002360548,0.001429873,0.002635355,0.002044845,0.002491904,0.0002460634],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00126333,"about_ca_system_score_gemma":0.002033221,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008694078,"about_ca_topic_score_gemma":0.007373078,"domain_scores_codex":[0.9940715,0.004630181,0.000178332,0.0003970255,0.0005873246,0.0001356479],"domain_scores_gemma":[0.9191429,0.07308815,0.001641467,0.003922671,0.00186946,0.0003352975],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001066429,0.00007160735,0.005203389,0.0001753287,0.0003400334,0.00008916082,0.0003008509,0.7399331,0.0003713352,0.1343892,0.001159724,0.1178595],"study_design_scores_gemma":[0.00001853905,0.00002816598,0.000306534,0.00003286503,0.00002470651,0.00002590282,0.00001802492,0.9335522,0.0001089024,0.06526484,0.0006098303,0.000009528543],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008914194,0.0003554052,0.9896901,0.0002511285,0.00002784595,0.00005187298,0.00003333421,0.0001204128,0.0005557312],"genre_scores_gemma":[0.2174308,0.0009437215,0.779865,0.0002964344,0.0001020871,0.0003555546,0.0001631033,0.0001083696,0.0007349227],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01855168,"threshold_uncertainty_score":0.09811181,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6865806864982038,"score_gpt":0.6435797549976086,"score_spread":0.04300093150059525,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}