{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3654501,0.002946964,0.008780839,0.007854655,0.003098271,0.008818237,0.007837966,0.01052814,0.001117251],"category_scores_gemma":[0.7013905,0.002044652,0.007482308,0.004918231,0.017364,0.008910326,0.008612079,0.01482062,0.001090484],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00357918,"about_ca_system_score_gemma":0.004622374,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002984796,"about_ca_topic_score_gemma":0.001787282,"domain_scores_codex":[0.5454236,0.3434803,0.03083358,0.02945612,0.04836409,0.002442291],"domain_scores_gemma":[0.2502541,0.6548974,0.02388303,0.05342305,0.01611953,0.001423012],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.002083289,0.0003560946,0.1260327,0.003844402,0.007001792,0.002250344,0.004404429,0.05947245,0.00279317,0.3536062,0.01689187,0.4212634],"study_design_scores_gemma":[0.0003338548,0.0009822726,0.01177511,0.00260393,0.001135028,0.00305182,0.0005142202,0.2044926,0.005095776,0.7494755,0.02008441,0.0004554335],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007512024,0.00263359,0.9846795,0.002569731,0.0004577252,0.0003019015,0.0001993817,0.0003160366,0.001330024],"genre_scores_gemma":[0.1871815,0.001097809,0.8051366,0.00331437,0.0007835389,0.001103933,0.0004590146,0.0003046106,0.0006187695],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.63455,"threshold_uncertainty_score":0.7825131,"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."}}