{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002537888,0.0001351756,0.0001655386,0.0000326484,0.0001442119,0.0002511712,0.0006298231,0.00003996392,0.000005321237],"category_scores_gemma":[0.00001391347,0.0001144873,0.00003861464,0.0001200518,0.00001644022,0.0004535918,0.0004683088,0.0000851295,0.000001441432],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002279478,"about_ca_system_score_gemma":0.0002051075,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000151336,"about_ca_topic_score_gemma":0.00006011747,"domain_scores_codex":[0.9987115,0.0000658123,0.0001416736,0.0005743242,0.0001935569,0.0003131193],"domain_scores_gemma":[0.9986866,0.00007028956,0.00005554605,0.0009878897,0.00008216985,0.0001175436],"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":[0.00001237342,0.0000400922,0.00001566971,0.00003711773,0.00002011008,0.0001018128,0.0005201473,0.001369024,0.0003046444,0.001037861,0.0004179061,0.9961233],"study_design_scores_gemma":[0.0006640702,0.0000452069,0.000008773122,0.00004961725,0.00001943445,0.00001139654,0.00002893163,0.9935408,0.002457307,0.001982544,0.001014804,0.0001771263],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003789148,0.000044944,0.9982363,0.0006463167,0.0002034684,0.0001370171,0.0002149321,0.00007857881,0.0000595383],"genre_scores_gemma":[0.01426198,0.000003294383,0.9847461,0.0006731605,0.00008831243,0.00001173221,0.00006762121,0.00001540091,0.0001324116],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9959461,"threshold_uncertainty_score":0.4668655,"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."}}