{"id":"W1970971885","doi":"10.1016/j.jclinepi.2011.10.019","title":"A confidence interval approach to sample size estimation for interobserver agreement studies with multiple raters and outcomes","year":2012,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":131,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University; York University","funders":"","keywords":"Confidence interval; Triage; Sample size determination; Reliability (semiconductor); Medicine; Estimation; Medical physics; Sample (material); Interval estimation; Statistics; Scale (ratio); Mathematics; Psychiatry; Power (physics)","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":[],"category_scores_codex":[0.3642608,0.003350027,0.008748183,0.01241768,0.002026312,0.00524682,0.01174666,0.007999947,0.00582587],"category_scores_gemma":[0.7199979,0.002682676,0.008032386,0.007963128,0.005384813,0.006480915,0.00518119,0.01112405,0.001018248],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0023272,"about_ca_system_score_gemma":0.004143605,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004969955,"about_ca_topic_score_gemma":0.002087053,"domain_scores_codex":[0.577203,0.3526362,0.0170115,0.02195777,0.02943282,0.001758728],"domain_scores_gemma":[0.148967,0.8083075,0.008988395,0.02125471,0.01180191,0.0006805764],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.003198505,0.0006857861,0.02168138,0.004338884,0.01209687,0.0008863711,0.004365866,0.06273738,0.001968174,0.2233619,0.01198817,0.6526906],"study_design_scores_gemma":[0.001330653,0.003185797,0.01876159,0.003513272,0.006352435,0.00281978,0.001096412,0.6489965,0.004376221,0.2857167,0.02329763,0.0005530592],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001414163,0.0008695023,0.9960803,0.0002082438,0.0001371345,0.0004222174,0.0001058842,0.0002208084,0.0005416806],"genre_scores_gemma":[0.08291865,0.0007531751,0.9103679,0.0003907332,0.0003259894,0.003864127,0.0003587076,0.0002234458,0.0007972484],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3642608,"threshold_uncertainty_score":0.7839797,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7278829789470725,"score_gpt":0.5892656106725227,"score_spread":0.1386173682745498,"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."}}