{"id":"W2071767222","doi":"10.1080/08839510902872223","title":"AN EMPIRICAL COMPARISON OF TECHNIQUES FOR HANDLING INCOMPLETE DATA USING DECISION TREES","year":2009,"lang":"en","type":"article","venue":"Applied Artificial Intelligence","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":152,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Society of Intestinal Research","funders":"","keywords":"Missing data; Imputation (statistics); Computer science; Spurious relationship; Decision tree; Robustness (evolution); Data mining; Decision tree learning; Machine learning; Statistics; Artificial intelligence; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1334847,0.001766016,0.001950904,0.006401319,0.001589456,0.003225029,0.003320985,0.002711663,0.001226065],"category_scores_gemma":[0.3822311,0.0008266727,0.003737486,0.007088171,0.002476889,0.008221205,0.003356976,0.00327009,0.0006197022],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002450915,"about_ca_system_score_gemma":0.002403244,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003506488,"about_ca_topic_score_gemma":0.003415764,"domain_scores_codex":[0.8772705,0.09538129,0.005597993,0.005401965,0.01504235,0.001305858],"domain_scores_gemma":[0.4297984,0.513047,0.01267623,0.0251411,0.01773753,0.001599648],"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":[0.00352492,0.0008386325,0.09421115,0.002314836,0.003702458,0.0002939139,0.004053049,0.4259643,0.001090104,0.01732475,0.006446022,0.4402359],"study_design_scores_gemma":[0.000358722,0.002795449,0.04470388,0.001802978,0.001300018,0.0008343115,0.002494506,0.8771544,0.003365227,0.05448408,0.01033644,0.0003699457],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4404857,0.01075147,0.5381097,0.002268281,0.000424331,0.0009788476,0.001420952,0.0007487084,0.004812041],"genre_scores_gemma":[0.7432156,0.003079715,0.2500071,0.0002600936,0.0001643232,0.0005600113,0.001915691,0.0002666839,0.0005306724],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1334847,"threshold_uncertainty_score":0.705943,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4797650739687325,"score_gpt":0.5540475740189142,"score_spread":0.07428250005018178,"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."}}