{"id":"W4387847841","doi":"10.31234/osf.io/bu6nt","title":"Check your outliers! An introduction to identifying statistical outliers in R with easystats","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Outlier; Univariate; Transparency (behavior); Computer science; Anomaly detection; Statistical analysis; Data mining; Multivariate statistics; Cover (algebra); Software; Statistical software; Statistical model; Statistics; Econometrics; Data science; Artificial intelligence; Machine learning; Mathematics; Engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001383122,0.0005005289,0.0009049709,0.0003821273,0.00008771668,0.0001625032,0.0003514411,0.0002841401,0.0001400677],"category_scores_gemma":[0.002824998,0.0004264617,0.00006304017,0.0002936829,0.00009499348,0.000155747,0.0004826777,0.001004355,0.00006546643],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003329061,"about_ca_system_score_gemma":0.0001487847,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002115267,"about_ca_topic_score_gemma":0.0008083288,"domain_scores_codex":[0.9961243,0.0003234742,0.0008441827,0.00139419,0.0006370869,0.0006767694],"domain_scores_gemma":[0.9975975,0.0005966799,0.0002083296,0.0009593118,0.0001941367,0.0004440238],"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":[0.0005628803,0.0005098956,0.0003849832,0.001924797,0.0001964661,0.0003291654,0.005788893,0.01610771,0.0002543176,0.9440475,0.008429768,0.02146368],"study_design_scores_gemma":[0.0005047229,0.0002239031,0.0008904352,0.0002324375,0.0001105054,0.000009315923,0.002959064,0.01204943,0.00008588387,0.9818501,0.0003351476,0.0007490784],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008575235,0.000005722459,0.986937,0.001231242,0.0009453205,0.001207981,0.0002701912,0.0003949534,0.0004322887],"genre_scores_gemma":[0.02529655,0.000008548082,0.9702913,0.00009103883,0.0005301497,0.0002682055,0.0001302025,0.0001729134,0.003211105],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03780263,"threshold_uncertainty_score":0.9998187,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3168746429933598,"score_gpt":0.4949494207395297,"score_spread":0.1780747777461699,"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."}}