{"id":"W1984322889","doi":"10.1002/env.628","title":"Robust principal component analysis and outlier detection with ecological data","year":2004,"lang":"en","type":"article","venue":"Environmetrics","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":95,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Outlier; Univariate; Mahalanobis distance; Principal component analysis; Bivariate analysis; Multivariate statistics; Robust statistics; Statistics; Anomaly detection; Computer science; Population; Data mining; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003907374,0.0001271765,0.0002752724,0.0001894225,0.00009938486,0.00002065572,0.0001476423,0.00007610673,0.00004185709],"category_scores_gemma":[0.0007559683,0.0000923218,0.00002762271,0.0005997103,0.000109497,0.00009515231,0.0001985728,0.0001714815,0.000005617689],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007054939,"about_ca_system_score_gemma":0.000006743979,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000011939,"about_ca_topic_score_gemma":0.00006702942,"domain_scores_codex":[0.998937,0.00005811909,0.0001928846,0.0003929104,0.0002297072,0.0001894146],"domain_scores_gemma":[0.9986864,0.0006093414,0.0000860158,0.0004933323,0.00000980839,0.0001150719],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0006012969,0.006501039,0.03678642,0.0003467128,0.003577946,0.0006011673,0.001053589,0.2833368,0.00361307,0.1854328,0.00010044,0.4780487],"study_design_scores_gemma":[0.004853689,0.001648081,0.4733661,0.00002769781,0.005176306,0.00009085114,0.0002885347,0.1377871,0.002239269,0.3674193,0.00544387,0.001659102],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1886279,0.00003347913,0.8109707,0.00002736684,0.00001791652,0.0001156607,0.00004028495,0.00002743442,0.0001392217],"genre_scores_gemma":[0.4617589,0.00003694076,0.5381033,0.00002002707,0.00001547922,0.000004412866,0.00001301636,0.000008897826,0.00003896054],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4763896,"threshold_uncertainty_score":0.3764774,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1912155192906799,"score_gpt":0.3618608260658264,"score_spread":0.1706453067751465,"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."}}