{"id":"W3211668472","doi":"10.1002/sta4.437","title":"A partial EM algorithm for model‐based clustering with highly diverse missing data patterns","year":2021,"lang":"en","type":"article","venue":"Stat","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; University of Waterloo","funders":"","keywords":"Missing data; Expectation–maximization algorithm; Computer science; Algorithm; Cluster analysis; Mixture model; Convergence (economics); Computation; Divergence (linguistics); Gaussian; Data mining; Mathematics; Artificial intelligence; Machine learning; Statistics; Maximum likelihood","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":[0.005617184,0.001645083,0.002181002,0.001859346,0.001368178,0.001636809,0.004007822,0.002160802,0.005385975],"category_scores_gemma":[0.01556658,0.001626856,0.002395608,0.002882787,0.001287383,0.002933135,0.003301786,0.003380021,0.002657435],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001026217,"about_ca_system_score_gemma":0.002861822,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005092362,"about_ca_topic_score_gemma":0.007839237,"domain_scores_codex":[0.9974234,0.001297047,0.0001690208,0.0005463592,0.0004683939,0.00009577043],"domain_scores_gemma":[0.9952285,0.003174185,0.0002670526,0.0006375134,0.0005945594,0.00009824541],"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":[0.0001614952,0.0001274712,0.001563811,0.0004716234,0.0005219469,0.0001588186,0.0003693625,0.4193369,0.003258307,0.06485466,0.01242814,0.4967475],"study_design_scores_gemma":[0.00003383512,0.00003179519,0.0003774897,0.00004523104,0.00003296568,0.0001506681,0.00004568144,0.9361702,0.001600063,0.0551092,0.006362014,0.00004091165],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005470788,0.00007163134,0.9987258,0.00005516586,0.00001092561,0.00003117341,0.0000477638,0.0002828925,0.000227589],"genre_scores_gemma":[0.01693621,0.000167287,0.9807073,0.0001146406,0.00002896936,0.0003151796,0.0005424927,0.0002024137,0.0009854722],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005617184,"threshold_uncertainty_score":0.0297069,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06896115937110447,"score_gpt":0.3166993067351346,"score_spread":0.2477381473640301,"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."}}