{"id":"W2164498941","doi":"10.1002/sim.2580","title":"A comparison of the ability of different propensity score models to balance measured variables between treated and untreated subjects: a Monte Carlo study","year":2006,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1134,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Toronto","funders":"","keywords":"Propensity score matching; Confounding; Observational study; Outcome (game theory); Statistics; Matching (statistics); Medicine; Average treatment effect; Variables; Econometrics; Mathematics","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":[0.0005536152,0.00022124,0.001050444,0.0000942553,0.00004009755,0.000004250564,0.0002079884,0.00006638189,0.000005034816],"category_scores_gemma":[0.001339533,0.0001347208,0.00001687129,0.0003598006,0.0003018177,0.00003709603,0.0001091193,0.0002048519,5.270307e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001091782,"about_ca_system_score_gemma":0.00003258875,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004236729,"about_ca_topic_score_gemma":0.003110834,"domain_scores_codex":[0.9979088,0.0002742489,0.00086632,0.0002780284,0.0004722729,0.0002002989],"domain_scores_gemma":[0.9976801,0.001033451,0.0003561664,0.0005111599,0.0003652949,0.00005382825],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001052001,0.0006317322,0.9803109,0.0003217201,0.00004533335,0.000004212744,0.003110252,0.0001714252,0.005874513,0.008849548,0.0002345956,0.0003405868],"study_design_scores_gemma":[0.001400583,0.0009609634,0.6867701,0.0007422187,0.0002353319,6.824714e-7,0.0005533664,0.00375957,0.01028509,0.2951308,6.144638e-7,0.0001606024],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9213251,0.00005099085,0.07656187,0.00003576731,0.00002073529,0.001686519,0.0001751684,0.0000431576,0.0001007148],"genre_scores_gemma":[0.9868041,0.000005662152,0.01307546,0.000005283802,0.00001612681,0.00004804089,0.000008825689,0.00001791994,0.00001858672],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2935407,"threshold_uncertainty_score":0.6404696,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2043349314626578,"score_gpt":0.4063998310840797,"score_spread":0.2020648996214219,"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."}}