{"id":"W3080534420","doi":"10.1145/3394486.3403106","title":"Missing Value Imputation for Mixed Data via Gaussian Copula","year":2020,"lang":"en","type":"article","venue":"","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":56,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institutes of Health Research; Office of Naval Research; Simons Institute for the Theory of Computing, University of California Berkeley; Defense Advanced Research Projects Agency; National Science Foundation","keywords":"Imputation (statistics); Missing data; Copula (linguistics); Computer science; Data mining; Ordinal data; Expectation–maximization algorithm; Gaussian; Algorithm; Statistics; Mathematics; Econometrics; Machine learning; Maximum likelihood","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01274584,0.0014409,0.003173111,0.002122944,0.001227375,0.002562249,0.004334542,0.001786801,0.00276147],"category_scores_gemma":[0.04399829,0.001372476,0.002966548,0.004217029,0.001527815,0.00385695,0.004177671,0.004258377,0.002013427],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001010858,"about_ca_system_score_gemma":0.002219121,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002721084,"about_ca_topic_score_gemma":0.002848612,"domain_scores_codex":[0.992386,0.004838892,0.0003982304,0.001088799,0.0009948908,0.0002932532],"domain_scores_gemma":[0.9814159,0.01223323,0.00125059,0.003274003,0.001492731,0.0003336601],"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":[0.0003392231,0.0001873634,0.01013939,0.0006570931,0.000973202,0.0007049788,0.0008379471,0.3552383,0.002786575,0.209177,0.01430886,0.4046501],"study_design_scores_gemma":[0.00002405082,0.00003040749,0.0006152288,0.00005293888,0.00004264759,0.0001773199,0.00005565148,0.8577586,0.001098222,0.1368827,0.003230674,0.00003154909],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0008580269,0.0001351671,0.9985653,0.00006291112,0.00001326056,0.00001522978,0.00005701374,0.0001828463,0.0001102438],"genre_scores_gemma":[0.07612028,0.0006832309,0.9198961,0.0002800748,0.0001277132,0.0002741341,0.001112618,0.0004010357,0.001104819],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01274584,"threshold_uncertainty_score":0.06740725,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2933176779152473,"score_gpt":0.4504668544550787,"score_spread":0.1571491765398313,"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."}}