{"id":"W4405942876","doi":"10.1093/biostatistics/kxae046","title":"Testing for a difference in means of a single feature after clustering","year":2024,"lang":"en","type":"article","venue":"Biostatistics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institute of General Medical Sciences; National Institute on Drug Abuse; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Cluster analysis; Type I and type II errors; Feature (linguistics); Computer science; Hierarchical clustering; Data mining; Statistical hypothesis testing; Algorithm; Word error rate; Pattern recognition (psychology); Statistics; Artificial intelligence; Mathematics","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":[0.00005303526,0.00009436678,0.0001016989,0.00003759242,0.00001396918,0.00002341006,0.00006780044,0.00008695392,0.000002070946],"category_scores_gemma":[0.0001474201,0.00008871141,0.00003526368,0.00008368504,0.00003764587,0.000001377005,0.00002514178,0.00004971795,5.231303e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001155463,"about_ca_system_score_gemma":0.00003873377,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000183492,"about_ca_topic_score_gemma":0.0002340421,"domain_scores_codex":[0.9994681,0.00001147899,0.0001381046,0.0001881474,0.00005118501,0.0001429159],"domain_scores_gemma":[0.9997403,0.00006148475,0.00002173014,0.0001016884,0.00004807877,0.00002670954],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000090787,0.00006456196,0.003136412,0.0004551863,0.00001441607,0.000009638918,0.0001345403,0.00002771094,0.9824482,0.00006709031,0.0002378792,0.01331358],"study_design_scores_gemma":[0.003835132,0.005166203,0.07849775,0.003156262,0.0002478701,0.00008676022,0.0004080877,0.1112295,0.7437839,0.002521253,0.04920673,0.001860579],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6944371,0.002083303,0.3016324,0.00009078767,0.0004759749,0.0003442515,0.0006560149,0.00002186619,0.0002582304],"genre_scores_gemma":[0.9547591,0.00001535874,0.04477077,0.00004640558,0.0001041443,0.00002604155,0.00006050129,0.00001964082,0.0001980106],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2603219,"threshold_uncertainty_score":0.3617547,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02388873090448533,"score_gpt":0.2522287114570061,"score_spread":0.2283399805525208,"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."}}