{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01608635,0.0009295085,0.001960202,0.003763631,0.001043138,0.003674713,0.003540898,0.00215102,0.004812097],"category_scores_gemma":[0.06868076,0.000883822,0.003121655,0.004724022,0.00179649,0.003857272,0.004666533,0.004264315,0.001775001],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001378816,"about_ca_system_score_gemma":0.003596416,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004852045,"about_ca_topic_score_gemma":0.00653645,"domain_scores_codex":[0.9860065,0.006729284,0.001148455,0.002725597,0.002886883,0.0005031498],"domain_scores_gemma":[0.9546245,0.03049464,0.001782593,0.005802637,0.006568236,0.0007274623],"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":[0.0004355126,0.0003007809,0.01815778,0.0005231272,0.0006004265,0.0005599526,0.0007974706,0.1942033,0.004359402,0.2418006,0.01996789,0.5182938],"study_design_scores_gemma":[0.00004639585,0.00005449771,0.001361822,0.00005041853,0.00002781239,0.0002544785,0.00007974667,0.8122197,0.001025395,0.1785385,0.006304786,0.00003629188],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002670531,0.00009145653,0.9961058,0.0001777621,0.00002652764,0.00006046874,0.0001480646,0.000366318,0.0003530695],"genre_scores_gemma":[0.0647824,0.0001181345,0.9316951,0.0002902699,0.0001135474,0.0003172444,0.0009432224,0.000404427,0.001335649],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01608635,"threshold_uncertainty_score":0.08507377,"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."}}