{"id":"W1973009402","doi":"10.1016/j.chemolab.2005.04.008","title":"Variance reduction in estimating classification error using sparse datasets","year":2005,"lang":"en","type":"article","venue":"Chemometrics and Intelligent Laboratory Systems","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":63,"is_retracted":false,"has_abstract":false,"ca_institutions":"National Research Council Canada; National Research Council Institute for Biodiagnostics","funders":"","keywords":"Estimator; Statistics; Resampling; Variance (accounting); Mathematics; Jackknife resampling; Sample size determination; Classifier (UML); Mean squared error; Computer science; Pattern recognition (psychology); Artificial intelligence","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":[0.008782641,0.0008036711,0.001925338,0.001552171,0.0005669186,0.001306197,0.001696648,0.001823314,0.0006949609],"category_scores_gemma":[0.04124681,0.001039612,0.001409828,0.001732191,0.001166141,0.00205922,0.001763425,0.002469729,0.0003891766],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000665051,"about_ca_system_score_gemma":0.001229644,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003543168,"about_ca_topic_score_gemma":0.003477472,"domain_scores_codex":[0.9943919,0.002931332,0.0003554448,0.0006966023,0.001407258,0.0002174666],"domain_scores_gemma":[0.9720162,0.02292137,0.0008412054,0.002072451,0.002005333,0.0001433849],"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":[0.0005380691,0.0002447703,0.003702776,0.0002799271,0.0003865108,0.00008828053,0.0002346335,0.466533,0.008250031,0.01911448,0.003351419,0.4972762],"study_design_scores_gemma":[0.00002098881,0.00003443226,0.0006794391,0.00001064619,0.00002789298,0.00003571553,0.00001226194,0.9871415,0.001858181,0.009853862,0.0003126752,0.00001245794],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01092382,0.0002104115,0.9882796,0.0001446128,0.00003098333,0.00002224641,0.00003570818,0.0002101698,0.000142454],"genre_scores_gemma":[0.2833005,0.0005444039,0.7128453,0.0002594409,0.0003261148,0.0002785724,0.0007515691,0.0002199402,0.001474136],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008782641,"threshold_uncertainty_score":0.04644758,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2556232352383119,"score_gpt":0.4383509325350697,"score_spread":0.1827276972967578,"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."}}