{"id":"W2138544379","doi":"10.1002/cjs.11248","title":"Prediction with missing data via Bayesian Additive Regression Trees","year":2015,"lang":"en","type":"preprint","venue":"Canadian Journal of Statistics","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Science Foundation","keywords":"Missing data; Imputation (statistics); Bayesian probability; Computer science; Random forest; Decision tree; Regression; Statistics; Parametric statistics; Artificial intelligence; Data mining; Machine learning; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006532326,0.000267551,0.0003888184,0.0003340796,0.0001699307,0.0005489837,0.002037695,0.0002038252,0.00002129229],"category_scores_gemma":[0.0002661151,0.0002155857,0.00003107862,0.0001638722,0.000139279,0.0004976307,0.0002501318,0.0009881653,0.000003925039],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003090627,"about_ca_system_score_gemma":0.00902319,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002569329,"about_ca_topic_score_gemma":0.01271041,"domain_scores_codex":[0.9980838,0.0001389009,0.0005426715,0.0004116454,0.0004772566,0.000345666],"domain_scores_gemma":[0.9958702,0.00009697808,0.0007570393,0.0009823649,0.001096572,0.001196842],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000502433,0.00004843544,0.001178001,0.0001382576,0.0002904963,0.003449066,0.00289564,0.008689277,0.00001897263,0.008116797,0.296273,0.6788518],"study_design_scores_gemma":[0.000457431,0.0004424926,0.001477653,0.002548984,0.0001664676,0.0008563905,0.0001363134,0.903279,0.00002829166,0.08393984,0.006137824,0.0005292893],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001106745,0.0005869911,0.9939603,0.0006599808,0.0009178005,0.00008408954,0.003252747,0.00001868282,0.0004087292],"genre_scores_gemma":[0.39763,0.00008310772,0.6011541,0.0001291693,0.0004752195,0.000001513186,0.0004261851,0.00003039924,0.00007022754],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8945897,"threshold_uncertainty_score":0.9965947,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08550463673936197,"score_gpt":0.2792063458812465,"score_spread":0.1937017091418845,"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."}}