{"id":"W2806528777","doi":"10.1101/333005","title":"Generalization of the minimum covariance determinant algorithm for categorical and mixed data types","year":2018,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Sensory Analysis and Statistical Methods","field":"Agricultural and Biological Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre; Western University; University of Toronto; Baycrest Hospital","funders":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Eisai; Government of Ontario; BioClinica; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; F. Hoffmann-La Roche; Bristol-Myers Squibb; Eli Lilly and Company; Strong; Biogen; Ontario Brain Institute; National Institute on Aging; Alzheimer's Association","keywords":"Categorical variable; Generalization; Covariance; Data type; Ordinal data; Mathematics; Computer science; Mahalanobis distance; Algorithm; Artificial intelligence; Statistics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006760515,0.0002219472,0.0003942502,0.0000146712,0.000185814,0.00008532947,0.000673841,0.0002565942,0.00002233584],"category_scores_gemma":[0.0005570811,0.00008828258,0.00008244981,0.0002781027,0.0001859318,0.00005409855,0.0005810841,0.0001443929,0.000001655319],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002158634,"about_ca_system_score_gemma":0.00004386286,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007372623,"about_ca_topic_score_gemma":0.00001766734,"domain_scores_codex":[0.9982888,0.0002469826,0.0003728918,0.0006666755,0.0001930131,0.0002316414],"domain_scores_gemma":[0.9984773,0.0003422555,0.0003209662,0.0004337874,0.0003310239,0.00009467618],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00003674619,0.0001616387,0.002599056,0.0001719881,0.0001824435,0.000005307106,0.000005666824,0.00001324162,0.9913678,0.001980016,0.001034728,0.002441344],"study_design_scores_gemma":[0.0004974192,0.0003380215,0.4599031,0.0002602336,0.0009093791,8.23328e-8,0.000008040552,0.1778004,0.3328505,0.0002746571,0.02588305,0.001275164],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9342695,0.0008123544,0.05910536,0.0004593321,0.00128832,0.0008192467,0.003181213,0.00006201944,0.000002577988],"genre_scores_gemma":[0.918864,0.0001413197,0.08014814,0.0001093007,0.0006780447,0.00004098761,0.000004932634,0.000005506208,0.000007788129],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6585174,"threshold_uncertainty_score":0.3600059,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05217688775488725,"score_gpt":0.2720762328793413,"score_spread":0.2198993451244541,"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."}}