{"id":"W4401090911","doi":"10.1080/03610918.2024.2378149","title":"On the prediction of rare events when sampling from large data","year":2024,"lang":"en","type":"article","venue":"Communications in Statistics - Simulation and Computation","topic":"Fire effects on ecosystems","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Canadian Statistical Sciences Institute; Natural Sciences and Engineering Research Council of Canada","keywords":"Statistics; Covariate; Sampling (signal processing); Stratified sampling; Logistic regression; Sampling design; Simple random sample; Range (aeronautics); Mathematics; Offset (computer science); Importance sampling; Computer science; Sample size determination; Sample (material); Stratum; Data mining; Econometrics; Monte Carlo method; Engineering","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"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":[0.04449924,0.000948742,0.001631846,0.001814636,0.001224763,0.001980014,0.002337163,0.001798432,0.001725569],"category_scores_gemma":[0.2163886,0.0009503469,0.001016095,0.002105328,0.003659796,0.002926024,0.002412091,0.002934076,0.0003808121],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001549761,"about_ca_system_score_gemma":0.001938651,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02157874,"about_ca_topic_score_gemma":0.02121951,"domain_scores_codex":[0.9852806,0.0112259,0.0004597362,0.001441558,0.001174334,0.0004178711],"domain_scores_gemma":[0.7044727,0.2762884,0.007673445,0.007090965,0.003354352,0.00112009],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004178776,0.00009950418,0.06901161,0.0002092542,0.0002697327,0.0008803807,0.0009472109,0.7655767,0.0007832075,0.07195066,0.002390286,0.08746354],"study_design_scores_gemma":[0.00003817264,0.00004419446,0.003211708,0.00005951952,0.0000243482,0.0001337099,0.00007754824,0.9615529,0.0004043226,0.03387247,0.0005586419,0.00002246906],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06239388,0.0005609465,0.9343544,0.0007993925,0.00006998657,0.0001332486,0.0001578327,0.000431497,0.00109897],"genre_scores_gemma":[0.7364992,0.0009579682,0.2578153,0.0006805889,0.0002461596,0.0005612118,0.0007360558,0.0002334158,0.002269978],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.04449924,"threshold_uncertainty_score":0.2353373,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1392180610278192,"score_gpt":0.3930839989121049,"score_spread":0.2538659378842858,"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."}}