{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002878906,0.0001060186,0.0002750386,0.0002308922,0.0002854734,0.0001537606,0.001578822,0.00007206355,0.0003726168],"category_scores_gemma":[0.006249886,0.00008415645,0.00005672167,0.0004680188,0.0002538208,0.0002871713,0.0008604047,0.000519483,0.00006512963],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006171963,"about_ca_system_score_gemma":0.0004340542,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002447218,"about_ca_topic_score_gemma":0.000003164884,"domain_scores_codex":[0.9971622,0.0002274255,0.0004999649,0.0003213658,0.001245284,0.0005437599],"domain_scores_gemma":[0.9923439,0.005692993,0.0001402104,0.0003888975,0.001145952,0.0002880385],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00236525,0.0008196111,0.002538523,0.0004756621,0.0005034204,0.003040081,0.0003864886,0.006583044,0.03356772,0.5533751,0.3548474,0.04149766],"study_design_scores_gemma":[0.003930394,0.001058914,0.06057068,0.0001158548,0.00003210942,0.0002265622,0.0001051798,0.7805397,0.001726136,0.1353134,0.01599404,0.0003869891],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02384795,0.00002905694,0.9664055,0.00764445,0.0004238361,0.0002119849,0.0008881491,0.00003462702,0.000514467],"genre_scores_gemma":[0.9026462,0.000007793374,0.09637301,0.00004500466,0.0002910661,0.000004965347,0.0002021648,0.000003056076,0.0004267672],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8787982,"threshold_uncertainty_score":0.7482149,"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."}}