{"id":"W1967689506","doi":"10.1016/j.jmva.2010.06.019","title":"On the layered nearest neighbour estimate, the bagged nearest neighbour estimate and the random forest method in regression and classification","year":2010,"lang":"en","type":"article","venue":"Journal of Multivariate Analysis","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":116,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies; Agence Nationale de la Recherche","keywords":"Mathematics; Independent and identically distributed random variables; Consistency (knowledge bases); Combinatorics; Nearest neighbour; Strong consistency; Random forest; Multivariate random variable; Weak consistency; k-nearest neighbors algorithm; Random variable; Statistics; Discrete mathematics; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007575289,0.0002756544,0.000817761,0.0002462477,0.0004478824,0.0003491,0.0004443491,0.0001503079,0.0001137963],"category_scores_gemma":[0.01917165,0.0001067761,0.0002468678,0.0007318693,0.0003420857,0.0001451556,0.0001094311,0.001109832,0.000003033056],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002652927,"about_ca_system_score_gemma":0.00007094405,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000428646,"about_ca_topic_score_gemma":0.0005789354,"domain_scores_codex":[0.9962007,0.001803945,0.0009563977,0.0002671725,0.0004894482,0.0002822716],"domain_scores_gemma":[0.9752557,0.02266901,0.001094122,0.0005500655,0.0002972921,0.0001337948],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004441763,0.0004732347,0.02716999,0.00009092629,0.002099566,0.00006383156,0.004148188,0.00365309,0.008317014,0.899926,0.0006401338,0.04897628],"study_design_scores_gemma":[0.003333268,0.00006724106,0.2191425,0.0001035035,0.001087701,0.00003277091,0.0002575969,0.5777045,0.0001070477,0.1979626,0.00006467946,0.000136604],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5558104,0.0001175462,0.4336237,0.009183722,0.0001820578,0.000488445,0.0000197128,0.00001529288,0.0005591447],"genre_scores_gemma":[0.8551602,0.00007455101,0.1444303,0.0001588928,0.00008585418,0.00001855125,0.000001600168,0.00002054855,0.0000495005],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7019634,"threshold_uncertainty_score":0.9890903,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05151034782966512,"score_gpt":0.4059097859689578,"score_spread":0.3543994381392927,"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."}}