{"id":"W2097433879","doi":"10.2202/1557-4679.1223","title":"A Pseudo-EM Algorithm for Clustering Incomplete Longitudinal Data","year":2010,"lang":"en","type":"article","venue":"The International Journal of Biostatistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Cholesky decomposition; Expectation–maximization algorithm; Covariance; Computer science; Focus (optics); Missing data; Data mining; Multivariate statistics; Algorithm; Multivariate normal distribution; Determining the number of clusters in a data set; CURE data clustering algorithm; Mathematics; Correlation clustering; Statistics; Artificial intelligence; Maximum likelihood; Machine learning","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001331106,0.0001004405,0.0001455871,0.00009181917,0.00008486264,0.0002999672,0.003872291,0.00003728587,0.000009670836],"category_scores_gemma":[0.0003143762,0.00006750949,0.00005861568,0.00007082069,0.00005354327,0.0003454654,0.0006666946,0.000297649,0.000003088172],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002164537,"about_ca_system_score_gemma":0.0001227698,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009613008,"about_ca_topic_score_gemma":0.00003860485,"domain_scores_codex":[0.9988093,0.00004111664,0.0003914137,0.0001623825,0.0004498362,0.0001459517],"domain_scores_gemma":[0.9979615,0.0005337615,0.000373995,0.0004791998,0.0005790018,0.00007256059],"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":[0.0000208123,0.00003880471,0.00002608369,0.000003994109,0.0001175745,0.00006018548,0.0002335348,0.00001255109,0.001887256,0.06987952,0.006347589,0.9213721],"study_design_scores_gemma":[0.0006111206,0.0001058232,0.0005270713,0.00003033645,0.00003187907,0.001394233,0.00001722502,0.8710575,0.000545651,0.1141626,0.01138223,0.0001342627],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005202328,0.00003305719,0.9925877,0.002823739,0.003649332,0.00007697929,0.0002343967,0.00001039335,0.00006416052],"genre_scores_gemma":[0.02878991,0.00002078977,0.9696928,0.000477237,0.0009508662,0.00000124706,0.00001088541,0.000008661152,0.0000476119],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9212378,"threshold_uncertainty_score":0.7195745,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05577961052628969,"score_gpt":0.3465629364035154,"score_spread":0.2907833258772257,"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."}}