{"id":"W7010393549","doi":"","title":"Interpretable data reduction in prediction modeling: extended redundancy analysis and its extensions and applications","year":2020,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Advanced Statistical Modeling Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Redundancy (engineering); Covariance; Data reduction; Statistical model; Statistical analysis; Data modeling; Reduction (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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01868464,0.001916011,0.001852956,0.002641414,0.0008572956,0.001924849,0.002038955,0.001101068,0.001967011],"category_scores_gemma":[0.04480168,0.0007731952,0.002877882,0.003625228,0.0020818,0.002946807,0.003588891,0.003395265,0.0009846926],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006938715,"about_ca_system_score_gemma":0.001727644,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002241377,"about_ca_topic_score_gemma":0.001796076,"domain_scores_codex":[0.9883985,0.008090351,0.0004564718,0.001188983,0.001632574,0.0002330963],"domain_scores_gemma":[0.9751747,0.01699978,0.001774589,0.003689279,0.002137226,0.0002244537],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002870625,0.0003249311,0.00555187,0.0009534395,0.0009191288,0.0005457028,0.002031509,0.1400097,0.005774824,0.2581157,0.008218156,0.577268],"study_design_scores_gemma":[0.0000397549,0.0002080548,0.002689658,0.0002390537,0.0001357272,0.0002738532,0.0002133707,0.6818061,0.002196237,0.3034734,0.008613708,0.0001111159],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005473794,0.001341158,0.9915853,0.0005705433,0.0000546021,0.00006909914,0.00009536053,0.0002136436,0.0005964417],"genre_scores_gemma":[0.1204809,0.002776273,0.8733987,0.000305145,0.0004158817,0.0004623854,0.0005251993,0.0002455977,0.001389875],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01868464,"threshold_uncertainty_score":0.09881502,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03704890159027037,"score_gpt":0.2984371172308644,"score_spread":0.261388215640594,"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."}}