{"id":"W2806096886","doi":"10.1016/j.csda.2018.05.015","title":"Addressing overfitting and underfitting in Gaussian model-based clustering","year":2018,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":false,"ca_institutions":"Okanagan University College; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Foundation for Innovation","keywords":"Overfitting; Cluster analysis; Maxima and minima; Mixture model; Expectation–maximization algorithm; Context (archaeology); Maxima; Computer science; Nonparametric statistics; Artificial intelligence; Convergence (economics); Machine learning; Gaussian; Mathematics; Mathematical optimization; Algorithm; Pattern recognition (psychology); Artificial neural network; Econometrics; Maximum likelihood; Statistics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04285782,0.002365278,0.004327373,0.003167885,0.002234807,0.004475574,0.006392639,0.005396612,0.0008768268],"category_scores_gemma":[0.1765395,0.002378627,0.002349886,0.004382834,0.004889856,0.007413322,0.008019827,0.007916679,0.0004074034],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002552324,"about_ca_system_score_gemma":0.004669429,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008480808,"about_ca_topic_score_gemma":0.009402578,"domain_scores_codex":[0.9694437,0.02067039,0.001593825,0.003639566,0.004010722,0.0006417987],"domain_scores_gemma":[0.9037501,0.07430913,0.00400252,0.01090107,0.006083525,0.0009537535],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004067662,0.0002473364,0.008990481,0.001015485,0.001103029,0.0002638928,0.001993411,0.6171983,0.003672572,0.1625874,0.004449474,0.1980719],"study_design_scores_gemma":[0.0000181504,0.000040243,0.0006371578,0.00005077416,0.00008667159,0.00008250857,0.00009792101,0.8673536,0.001086596,0.1294996,0.001008676,0.00003819208],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006168493,0.0004774444,0.9926476,0.0003071,0.00003451833,0.00002877087,0.00002629497,0.0001513986,0.0001583519],"genre_scores_gemma":[0.3007716,0.001485785,0.6932752,0.0007971135,0.0003582915,0.0003968122,0.0005836645,0.0006039663,0.001727671],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.04285782,"threshold_uncertainty_score":0.2266566,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1142948983470015,"score_gpt":0.3791082464019549,"score_spread":0.2648133480549534,"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."}}