{"id":"W2016403661","doi":"10.1002/bimj.200810488","title":"Some Methods of Propensity‐Score Matching had Superior Performance to Others: Results of an Empirical Investigation and Monte Carlo simulations","year":2009,"lang":"en","type":"article","venue":"Biometrical Journal","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":769,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Toronto","funders":"","keywords":"Propensity score matching; Statistics; Monte Carlo method; Matching (statistics); Standard deviation; Logit; Mathematics; Medicine","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001143927,0.0001441752,0.000403316,0.001016668,0.00009120425,0.0000436814,0.0001857574,0.0001115364,0.000003976335],"category_scores_gemma":[0.002274567,0.000112685,0.00005423292,0.001500137,0.00009686274,0.0006140191,0.0000514174,0.0002613492,3.768705e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007911846,"about_ca_system_score_gemma":0.00006110704,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001297406,"about_ca_topic_score_gemma":0.000001674067,"domain_scores_codex":[0.9982947,0.0002146791,0.0007475152,0.0001862461,0.0003594303,0.0001974513],"domain_scores_gemma":[0.9983543,0.0005239095,0.0003485568,0.0002251543,0.000304389,0.0002437187],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007675074,0.0007556958,0.02281027,0.0001920886,0.00009058374,0.00002144319,0.007186863,0.001493972,0.6800453,0.002094366,0.0003360543,0.2842058],"study_design_scores_gemma":[0.001950689,0.006273846,0.2810068,0.0007031971,0.0001385465,0.000245674,0.0003950355,0.01346501,0.4268679,0.2680264,0.0002131896,0.0007136629],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9511,0.00007823835,0.04814072,0.0003427393,0.00002936921,0.0002271633,0.00001521762,0.00004474408,0.00002184542],"genre_scores_gemma":[0.6206691,0.00001876545,0.3791653,0.00007651695,0.00005013349,0.000001039903,7.898624e-7,0.00000890998,0.000009400995],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3310246,"threshold_uncertainty_score":0.4595162,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.374473599393049,"score_gpt":0.4837530024844751,"score_spread":0.109279403091426,"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."}}