{"id":"W2917654268","doi":"","title":"A method of determining the winsorization threshold, with an application to domain estimation","year":2015,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Statistics Canada; Université de Montréal","funders":"","keywords":"Estimator; Context (archaeology); Consistency (knowledge bases); Constant (computer programming); Estimation; Econometrics; Statistics; Sample (material); Population; Computer science; Mathematics; Economics; Physics; Geology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008838742,0.0002711031,0.0004149376,0.0001335769,0.0001897281,0.0001957253,0.0009131916,0.000192717,0.00002133783],"category_scores_gemma":[0.003335988,0.0002060905,0.00006662858,0.0004168489,0.0001491913,0.0001163002,0.0004905763,0.0003625852,0.00000538142],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009191917,"about_ca_system_score_gemma":0.0002445011,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002448465,"about_ca_topic_score_gemma":0.0004691059,"domain_scores_codex":[0.9937555,0.004344771,0.000583693,0.0005713945,0.0005259994,0.0002186826],"domain_scores_gemma":[0.9913216,0.003137453,0.0007083809,0.001844523,0.002816385,0.0001716605],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003239904,0.0003021796,0.0006665157,0.0001832009,0.00003308446,4.703262e-7,0.008622252,0.0002068918,0.0004929613,0.7599685,0.0001122254,0.2293793],"study_design_scores_gemma":[0.0003866137,0.000003668378,0.002026953,0.000978519,0.00009915239,0.000004871199,0.0001823364,0.1587401,0.007135249,0.8298492,0.0002719999,0.0003213151],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01830017,0.00001808486,0.9732709,0.001541647,0.00004142479,0.0009573818,0.00006220764,0.000102835,0.005705377],"genre_scores_gemma":[0.1306896,0.000005752974,0.8687395,0.00004336021,0.00001641859,0.0001895419,0.0001662023,0.00004030392,0.0001093236],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.229058,"threshold_uncertainty_score":0.8404125,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04197165859373145,"score_gpt":0.3425491466978793,"score_spread":0.3005774881041478,"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."}}