{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01865876,0.001054919,0.002481704,0.002018081,0.0008177232,0.001891712,0.003593357,0.001636588,0.003064901],"category_scores_gemma":[0.07085655,0.0009782168,0.001646087,0.003269727,0.001291982,0.002982402,0.002298661,0.003744029,0.0008662018],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008789717,"about_ca_system_score_gemma":0.001729283,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005631817,"about_ca_topic_score_gemma":0.005295029,"domain_scores_codex":[0.9893447,0.007581893,0.0003355442,0.001041518,0.001352575,0.0003438564],"domain_scores_gemma":[0.9592568,0.03304358,0.002417727,0.002399645,0.002367307,0.0005148449],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000269918,0.0001439612,0.009645079,0.000264075,0.0004691802,0.0002538178,0.0003642595,0.6812956,0.000589982,0.1327566,0.007565053,0.1663825],"study_design_scores_gemma":[0.00001752263,0.00001752169,0.0004167774,0.00003177216,0.00003110725,0.00002998024,0.00001537004,0.9038584,0.0001933281,0.09436343,0.00100815,0.00001656855],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006553642,0.0002201366,0.992187,0.0002908575,0.00003752623,0.00001898163,0.0001156849,0.0002107267,0.0003654665],"genre_scores_gemma":[0.423487,0.0008915974,0.5711405,0.0004191557,0.0003343688,0.000257524,0.001066643,0.0002250046,0.002178239],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01865876,"threshold_uncertainty_score":0.09867811,"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."}}