{"id":"W2093156537","doi":"10.1007/s10044-007-0088-4","title":"Hierarchical clustering of subpopulations with a dissimilarity based on the likelihood ratio statistic: application to clustering massive data sets","year":2007,"lang":"en","type":"article","venue":"Pattern Analysis and Applications","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Cluster analysis; Mathematics; Statistic; Hierarchical clustering; Multinomial distribution; Poisson distribution; Multivariate normal distribution; Statistics; Data mining; Computer science; Multivariate statistics","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":[0.005676434,0.0006505508,0.001667396,0.003758933,0.001363179,0.001789392,0.001935302,0.001322725,0.00112186],"category_scores_gemma":[0.02383688,0.0004696299,0.001537811,0.003351384,0.001098542,0.001647538,0.002391593,0.001325374,0.0004261835],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001043909,"about_ca_system_score_gemma":0.001144884,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002334434,"about_ca_topic_score_gemma":0.002744782,"domain_scores_codex":[0.9974428,0.001221838,0.000158481,0.0004536676,0.0006278364,0.0000952978],"domain_scores_gemma":[0.9923184,0.004600445,0.0008729516,0.0009341915,0.0009749034,0.0002991171],"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":[0.0008912798,0.000368056,0.01735653,0.0005952977,0.0006520575,0.0004368607,0.001567556,0.4425353,0.02074042,0.061276,0.004158315,0.4494223],"study_design_scores_gemma":[0.00005204146,0.0001000043,0.002413548,0.00001394974,0.00003925412,0.0001440982,0.0001046569,0.9652669,0.001994581,0.02890367,0.00092347,0.0000437915],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0270192,0.0001413865,0.9719282,0.0001040734,0.00001607237,0.00007270413,0.00006828253,0.0003723017,0.0002778647],"genre_scores_gemma":[0.2771519,0.0001136216,0.7213452,0.00004522343,0.00005319113,0.000187807,0.0003200974,0.0001792831,0.0006037787],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005676434,"threshold_uncertainty_score":0.03002024,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03091776160389113,"score_gpt":0.3354578783523037,"score_spread":0.3045401167484125,"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."}}