{"id":"W4284990586","doi":"10.1080/02664763.2022.2097204","title":"A flexible test for early-stage studies with multiple endpoints","year":2022,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Behavioral and Psychological Studies","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute on Aging; Institute of Aging; University of Kansas Medical Center; National Institutes of Health; National Center for Advancing Translational Sciences; University of Kansas","keywords":"Null hypothesis; Parametric statistics; Statistical hypothesis testing; Computer science; Statistics; Test (biology); Type I and type II errors; Null (SQL); Econometrics; Sample size determination; Mathematics; Machine learning; Data mining","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003877223,0.0001614581,0.0004045601,0.00007273717,0.0003487581,0.00001754624,0.0002098312,0.00003371999,0.0006387029],"category_scores_gemma":[0.00007695865,0.0001113286,0.00006160008,0.0001597437,0.000130029,0.00002271237,0.00007518844,0.0003630452,0.00001672207],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006435546,"about_ca_system_score_gemma":0.00002149564,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009129054,"about_ca_topic_score_gemma":0.00001117908,"domain_scores_codex":[0.9987323,0.00003316112,0.0004551027,0.0001851458,0.0003049999,0.0002892815],"domain_scores_gemma":[0.9981019,0.001023352,0.0004718081,0.0001370013,0.0001838704,0.00008206866],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.02154708,0.006740368,0.1152113,0.000222604,0.002948301,0.001556777,0.03593062,0.0007771497,0.002174966,0.1181926,0.5671868,0.1275115],"study_design_scores_gemma":[0.01872275,0.02305384,0.2555037,0.00004656423,0.000868957,0.0003545939,0.05406529,0.00003209291,0.0006229099,0.03894814,0.6065523,0.001228808],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8519652,0.002285298,0.1131949,0.001009917,0.003611477,0.002059116,0.006636936,0.0001307144,0.01910641],"genre_scores_gemma":[0.9596238,0.00004141827,0.03601921,0.0004042767,0.0001862934,0.0001968523,0.000009942545,0.00002885079,0.003489343],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1402924,"threshold_uncertainty_score":0.6993349,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2145963413119941,"score_gpt":0.3837530015081179,"score_spread":0.1691566601961238,"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."}}