{"id":"W4383682235","doi":"10.3329/jsr.v56i2.67469","title":"Penalized logistic normal multinomial factor analyzers for high dimensional compositional data","year":2023,"lang":"en","type":"article","venue":"Journal of Statistical Research","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Mixture model; Expectation–maximization algorithm; Computer science; Multinomial distribution; Lasso (programming language); Multinomial logistic regression; Statistics; Algorithm; Computation; Mathematics; Maximum likelihood","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":[0.00857376,0.001371656,0.001173505,0.001197978,0.0007965181,0.001463258,0.002428534,0.00140419,0.003452021],"category_scores_gemma":[0.0202518,0.0008445727,0.001815939,0.001450711,0.00161646,0.002623003,0.002474641,0.002911355,0.001363564],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001270348,"about_ca_system_score_gemma":0.001987883,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006620381,"about_ca_topic_score_gemma":0.008997368,"domain_scores_codex":[0.9954562,0.002882903,0.0002034239,0.0007148361,0.00053601,0.0002066717],"domain_scores_gemma":[0.9909271,0.006310385,0.000790217,0.0008507256,0.0008431768,0.0002783691],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0005758933,0.0001464092,0.008994653,0.0002184845,0.0002573167,0.0002936478,0.0004108463,0.680288,0.005471179,0.09602602,0.007786169,0.1995314],"study_design_scores_gemma":[0.000008278334,0.00001544989,0.0002716714,0.000009241633,0.000006308127,0.000040286,0.00001568706,0.9845765,0.0003869792,0.01367116,0.0009848679,0.00001361829],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004900135,0.0001045622,0.9942083,0.0001437275,0.00001438455,0.0000276489,0.00008746987,0.0003085668,0.00020511],"genre_scores_gemma":[0.2022447,0.0003761049,0.7906168,0.0002845014,0.0001066771,0.0004975963,0.001275424,0.0004817401,0.004116409],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00857376,"threshold_uncertainty_score":0.04534292,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2802023624603979,"score_gpt":0.4537713282034169,"score_spread":0.173568965743019,"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."}}