{"id":"W3176979971","doi":"10.1002/sim.9097","title":"Estimation of diagnostic test accuracy: A “Rule of Three” for data with repeated observations but without a gold standard","year":2021,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; Impact","funders":"","keywords":"Multinomial distribution; Statistics; Computer science; Goodness of fit; Gold standard (test); Degrees of freedom (physics and chemistry); Test (biology); Mathematics","routes":{"ca_aff":true,"ca_fund":false,"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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0009435129,0.0001604658,0.0006611815,0.00007921649,0.00003302827,0.000009136387,0.0002545649,0.00005999057,0.00008974248],"category_scores_gemma":[0.281646,0.0001229307,0.00001351345,0.0004142095,0.0003175935,0.00007649609,0.00008401642,0.0001473711,3.826189e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003455729,"about_ca_system_score_gemma":0.0003171929,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001552816,"about_ca_topic_score_gemma":0.0006788134,"domain_scores_codex":[0.998103,0.00008941894,0.0008648462,0.0003140354,0.0004318391,0.0001969099],"domain_scores_gemma":[0.9438755,0.05413629,0.0004460144,0.0007653043,0.0007086646,0.0000682295],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002268749,0.0003795773,0.02661931,0.002527304,0.0001059384,0.00007567083,0.0005685714,0.00003577179,0.001250562,0.8482581,0.005848593,0.1141037],"study_design_scores_gemma":[0.002119111,0.0007269184,0.01195901,0.002032338,0.0003525664,0.00001278425,0.0002552393,0.08675032,0.001095241,0.8944342,0.00009399552,0.0001682366],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00521742,0.00008142912,0.9862501,0.0003501914,0.00007146655,0.0005122803,0.007313106,0.00001800403,0.0001859974],"genre_scores_gemma":[0.07775173,0.00006021506,0.9213197,0.00003532464,0.00003278736,0.00004535965,0.0006905358,0.00002439479,0.00004001864],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2807025,"threshold_uncertainty_score":0.724405,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1483904432595583,"score_gpt":0.4300721741808364,"score_spread":0.2816817309212781,"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."}}