{"id":"W2095752327","doi":"10.1002/(sici)1097-0258(20000315)19:5<723::aid-sim379>3.0.co;2-a","title":"Interval estimation for Cohen's kappa as a measure of agreement","year":2000,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":217,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Confidence interval; Statistics; Mathematics; Measure (data warehouse); Kappa; Statistic; Variance (accounting); Delta method; Coverage probability; Asymptotic analysis; Computation; Asymptotic distribution; Cohen's kappa; Applied mathematics; Computer science; Algorithm","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":[],"consensus_categories":[],"category_scores_codex":[0.0671707,0.0009194962,0.002020541,0.01051445,0.001272814,0.003126918,0.004042391,0.001764458,0.005610983],"category_scores_gemma":[0.351872,0.0004554826,0.002152083,0.007647032,0.002175091,0.003753557,0.00385122,0.003072929,0.001801827],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001567063,"about_ca_system_score_gemma":0.002102059,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001530363,"about_ca_topic_score_gemma":0.0008842369,"domain_scores_codex":[0.8824344,0.07347108,0.009351484,0.008111298,0.0255265,0.001105324],"domain_scores_gemma":[0.7267736,0.220119,0.01426846,0.01160473,0.02636991,0.0008644462],"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":[0.001362526,0.0002520107,0.02050437,0.004183941,0.001781927,0.0003224274,0.004410565,0.02588647,0.003158843,0.1969858,0.02644013,0.714711],"study_design_scores_gemma":[0.0003359136,0.002555149,0.05820322,0.004742139,0.001664742,0.003483329,0.0034158,0.2608244,0.01144719,0.5630474,0.08938649,0.0008941182],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01449865,0.004029885,0.9684323,0.0003412143,0.0004213856,0.0004896483,0.0006398733,0.0007902564,0.01035678],"genre_scores_gemma":[0.2301384,0.002170677,0.7607723,0.0002709093,0.0004029033,0.003491173,0.001069422,0.0004346769,0.001249576],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0671707,"threshold_uncertainty_score":0.3552369,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1194851870437682,"score_gpt":0.4260948892710158,"score_spread":0.3066097022272476,"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."}}