{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03113225,0.00341018,0.002684454,0.005843231,0.001175921,0.005308284,0.005640876,0.003064799,0.1499429],"category_scores_gemma":[0.2211461,0.003134267,0.00410609,0.00592468,0.003044392,0.006892591,0.005575445,0.008301831,0.122643],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009551093,"about_ca_system_score_gemma":0.003719936,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001419343,"about_ca_topic_score_gemma":0.00287078,"domain_scores_codex":[0.9715594,0.01770982,0.003213935,0.001694218,0.005206044,0.000616547],"domain_scores_gemma":[0.7733829,0.1841843,0.01051679,0.0185439,0.01129981,0.002072311],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002271797,0.00006967955,0.001815675,0.003673382,0.0002724116,0.000486621,0.0006631829,0.002878411,0.001949764,0.03500918,0.8206471,0.1323074],"study_design_scores_gemma":[0.0002316058,0.0001323429,0.002778434,0.002160932,0.0001016384,0.001017872,0.0001990738,0.01008872,0.003414086,0.1136888,0.8658748,0.0003116347],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0009107991,0.00332261,0.7931834,0.006525185,0.003376077,0.0005886048,0.02035272,0.162586,0.009154584],"genre_scores_gemma":[0.01045358,0.003463479,0.8622388,0.00541834,0.002493204,0.003967223,0.01045639,0.09128124,0.01022778],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9688678,"threshold_uncertainty_score":0.501609,"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."}}