{"id":"W6958187160","doi":"10.60692/3q8d1-68e80","title":"From Black Box to Shining Spotlight: Using Random Forest Prediction Intervals to Illuminate the Impact of Assumptions in Linear Regression","year":2022,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Statistics Education and Methodologies","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; University of British Columbia","funders":"","keywords":"Random forest; Black box; Regression; Linear regression; Prediction interval; Reputation; Regression analysis; Proper linear model","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":[0.01166126,0.0009768654,0.0008431636,0.002329607,0.00072266,0.003968095,0.001836166,0.002197339,0.008871271],"category_scores_gemma":[0.08317426,0.0008173309,0.00106853,0.001617451,0.001599878,0.006542983,0.003325197,0.003967253,0.002265097],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005730366,"about_ca_system_score_gemma":0.0008590966,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002634377,"about_ca_topic_score_gemma":0.003197671,"domain_scores_codex":[0.9951485,0.003039885,0.000228469,0.0005144083,0.0009182029,0.0001505844],"domain_scores_gemma":[0.8973013,0.0927626,0.002625739,0.004178124,0.00258948,0.0005427787],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002000978,0.0002877109,0.01630937,0.001369341,0.0002025224,0.001807367,0.009395352,0.08067423,0.01080787,0.2016734,0.06861689,0.6068549],"study_design_scores_gemma":[0.0003106308,0.0004939461,0.006356445,0.001563284,0.0001163318,0.001522139,0.001657131,0.5601504,0.01791239,0.3235267,0.0860709,0.0003197717],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0308194,0.001335787,0.9427056,0.004053459,0.0003800348,0.00008669689,0.0006769656,0.0133071,0.006634944],"genre_scores_gemma":[0.2804029,0.0009626754,0.7096087,0.001554183,0.0003719601,0.0003135453,0.0005923958,0.00337435,0.002819175],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9883387,"threshold_uncertainty_score":0.06167138,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2083367864900016,"score_gpt":0.3898779068496603,"score_spread":0.1815411203596587,"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."}}