{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002792418,0.00007998345,0.0001555092,0.00001080033,0.00005882356,0.00004315033,0.0001954763,0.00003949055,0.000185217],"category_scores_gemma":[0.004252877,0.00006334287,0.00002233185,0.0000700382,0.00002003532,0.00007211282,0.00007899888,0.00005225593,0.00001711518],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008084346,"about_ca_system_score_gemma":0.00002547052,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001306846,"about_ca_topic_score_gemma":0.000001942117,"domain_scores_codex":[0.9992523,0.00005970998,0.000222094,0.0002260443,0.0001038195,0.0001360631],"domain_scores_gemma":[0.9983433,0.001200992,0.00005902573,0.0002457617,0.00003898425,0.0001119288],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002338098,0.00003197611,0.00003186133,0.0002103054,0.00001894214,0.000001871598,0.0001982263,0.000002272247,0.002022995,0.7366611,0.02267434,0.2381227],"study_design_scores_gemma":[0.0002147122,0.00006163843,0.0001221776,0.00001356305,0.00003259857,0.000001235955,0.00005020637,0.3829525,0.001338306,0.6135746,0.001547297,0.00009114078],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004316223,0.000008399754,0.9935709,0.003106645,0.0000842744,0.0002116132,0.00007476653,0.00007139061,0.002440346],"genre_scores_gemma":[0.05610242,7.185739e-7,0.9429703,0.000697622,0.0001019349,0.000005963206,0.00005247724,0.00001465136,0.0000539554],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3829503,"threshold_uncertainty_score":0.5091398,"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."}}