{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004113966,0.0001335865,0.0002824377,0.00007955485,0.0001356879,0.0001308151,0.0009536272,0.00002662906,0.00003126899],"category_scores_gemma":[0.02575179,0.00006102618,0.0001129646,0.00009102379,0.0003308829,0.0001707311,0.0001740547,0.00014133,9.10318e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007405372,"about_ca_system_score_gemma":0.0000755367,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002003962,"about_ca_topic_score_gemma":0.0001547477,"domain_scores_codex":[0.9970289,0.0001053058,0.00116739,0.0001661636,0.001400865,0.0001313647],"domain_scores_gemma":[0.9857738,0.0104351,0.001269922,0.0002525876,0.002223991,0.00004462379],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.01482201,0.002080193,0.547716,0.00074401,0.006213073,0.00002400472,0.0172447,0.03111898,0.07179476,0.04494015,0.06721252,0.1960896],"study_design_scores_gemma":[0.01558455,0.006142671,0.2742167,0.001239144,0.0010018,0.0001133647,0.01439831,0.1746508,0.01906436,0.4832476,0.009562142,0.0007785992],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6872414,0.00003646775,0.304521,0.005011971,0.002003114,0.0005767656,0.0006028786,0.000002112089,0.000004281791],"genre_scores_gemma":[0.8858047,0.00001290703,0.1137049,0.000299639,0.0000769631,0.00001203056,0.000003935047,0.000006858631,0.00007806447],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4383075,"threshold_uncertainty_score":0.9824547,"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."}}