{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001617212,0.0001492487,0.0003119342,0.0004279159,0.0001762606,0.00006009687,0.0002205702,0.00005013519,0.00008140914],"category_scores_gemma":[0.0008306979,0.00009861329,0.0001011067,0.000410616,0.00002306458,0.0002124555,0.0001663546,0.0001456526,0.00004956916],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003650411,"about_ca_system_score_gemma":0.00006797467,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001532526,"about_ca_topic_score_gemma":0.000002114683,"domain_scores_codex":[0.9980866,0.0004362267,0.0008552753,0.0001280211,0.0003128756,0.0001809707],"domain_scores_gemma":[0.9987042,0.0002543744,0.000455081,0.0003648915,0.0001491046,0.00007237071],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0005743509,0.00001610074,0.07187372,0.0001981897,0.00008483636,0.000001650024,0.8507002,0.07286353,0.00007429744,0.0003188301,0.002939527,0.0003547796],"study_design_scores_gemma":[0.004164229,0.000403354,0.2005587,0.001521453,0.0001636422,0.00004447949,0.5737467,0.2162174,0.001593007,0.0006646874,0.0003798172,0.0005426239],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7845929,0.000001123806,0.2130464,0.00006546205,0.00067272,0.0006490154,0.0007559217,0.00006335627,0.000153185],"genre_scores_gemma":[0.981999,8.892639e-8,0.01761933,0.00004327016,0.00007180325,0.0001288373,0.00004226114,0.00001351926,0.00008183774],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2769535,"threshold_uncertainty_score":0.4021333,"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."}}