{"id":"W1978765295","doi":"10.2202/1557-4679.1275","title":"Sample Size Requirements for Interval Estimation of the Kappa Statistic for Interobserver Agreement Studies with a Binary Outcome and Multiple Raters","year":2010,"lang":"en","type":"article","venue":"The International Journal of Biostatistics","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":127,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Statistics; Cohen's kappa; Confidence interval; Kappa; Intraclass correlation; Mathematics; Interval estimation; Statistic; Sample size determination; Sample (material); Binary number; Limit (mathematics); Interval (graph theory); Psychometrics; Combinatorics","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":[0.1786186,0.001069426,0.002989158,0.005049699,0.001218996,0.002704979,0.004168657,0.004818264,0.01082509],"category_scores_gemma":[0.5975481,0.001106063,0.001674337,0.002851962,0.001620932,0.002699228,0.002839935,0.002883696,0.003594608],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00103512,"about_ca_system_score_gemma":0.002557308,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006303696,"about_ca_topic_score_gemma":0.0006430093,"domain_scores_codex":[0.7999874,0.1302816,0.02078545,0.004278774,0.04277185,0.001894894],"domain_scores_gemma":[0.245363,0.7036695,0.009069589,0.01281633,0.02805889,0.001022686],"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":[0.01426279,0.001348018,0.02602221,0.005384203,0.0004330233,0.002024927,0.004638802,0.03668181,0.02051931,0.146358,0.04766413,0.6946628],"study_design_scores_gemma":[0.008194519,0.02397966,0.09354905,0.01098537,0.001428294,0.0112449,0.003447028,0.3083707,0.08315584,0.3014544,0.1532092,0.0009808949],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0171504,0.001270079,0.9575879,0.001334542,0.0005864576,0.008586189,0.001186311,0.0006231448,0.01167502],"genre_scores_gemma":[0.1367383,0.001020211,0.8089746,0.0013515,0.0005279917,0.04652979,0.001939634,0.0005959983,0.002321908],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8213813,"threshold_uncertainty_score":0.9446369,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2216258336390316,"score_gpt":0.4380071238304545,"score_spread":0.2163812901914229,"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."}}