{"id":"W2609185034","doi":"10.1186/s12874-017-0338-0","title":"Double-adjustment in propensity score matching analysis: choosing a threshold for considering residual imbalance","year":2017,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":491,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hamilton Health Sciences; McMaster University; Population Health Research Institute","funders":"University of Oxford; Cancer Research UK","keywords":"Covariate; Propensity score matching; Confounding; Statistics; Residual; Matching (statistics); Logistic regression; Regression; Mathematics; Regression analysis; Econometrics; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.06941801,0.0009543284,0.001737593,0.001402466,0.0008438102,0.001565041,0.002064843,0.001619828,0.001819712],"category_scores_gemma":[0.1776288,0.0006040176,0.002167034,0.001739772,0.001880939,0.002116708,0.002513743,0.002156743,0.0002565408],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008855787,"about_ca_system_score_gemma":0.002236418,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001363129,"about_ca_topic_score_gemma":0.001299551,"domain_scores_codex":[0.9553469,0.03528474,0.002519446,0.003289063,0.002795828,0.0007640489],"domain_scores_gemma":[0.8937799,0.08483876,0.008100331,0.01004067,0.002545616,0.000694756],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.005074192,0.0006712202,0.1529049,0.002671024,0.004823809,0.001391796,0.00274634,0.1283654,0.01785288,0.1035447,0.007271467,0.5726824],"study_design_scores_gemma":[0.001056088,0.002276202,0.03577777,0.0006992397,0.001812976,0.001455852,0.0003686956,0.666053,0.02089773,0.256198,0.01313734,0.0002670366],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03188892,0.0005892638,0.9656529,0.0005447534,0.0001145814,0.0003670945,0.0000696229,0.0003500978,0.0004227745],"genre_scores_gemma":[0.5114285,0.0002380622,0.4863264,0.0003842831,0.0001095765,0.0008301976,0.0001727486,0.0001652647,0.0003450406],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.930582,"threshold_uncertainty_score":0.3671219,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8896096151371321,"score_gpt":0.6436425630183503,"score_spread":0.2459670521187818,"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."}}