{"id":"W2146976162","doi":"10.1002/(sici)1097-0258(20000215)19:3<373::aid-sim337>3.0.co;2-y","title":"Testing the equality of two dependent kappa statistics","year":2000,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":89,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph; Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Statistics; Kappa; Correlation; Monte Carlo method; Mathematics; Cohen's kappa; Goodness of fit; Dependency (UML); Sample size determination; Variable (mathematics); Computer science; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"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":[0.2024872,0.001724252,0.00346632,0.01081366,0.002679649,0.004627347,0.004520973,0.00304675,0.006440107],"category_scores_gemma":[0.6414766,0.001136942,0.003469868,0.005554335,0.008107116,0.006132675,0.008412695,0.003641232,0.002040525],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002056354,"about_ca_system_score_gemma":0.004251299,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001444876,"about_ca_topic_score_gemma":0.001068565,"domain_scores_codex":[0.6833567,0.2018484,0.02441823,0.02663719,0.06068893,0.003050507],"domain_scores_gemma":[0.2930488,0.58917,0.03147649,0.04178861,0.04199441,0.00252169],"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":[0.00485243,0.0004249489,0.08294743,0.003998037,0.005079336,0.001206204,0.01164089,0.02395484,0.009584379,0.2162581,0.01214763,0.6279057],"study_design_scores_gemma":[0.00121013,0.005388763,0.1578186,0.002839608,0.002276931,0.00619514,0.008677211,0.1980949,0.03148092,0.5421497,0.04215,0.00171808],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0582719,0.000765665,0.927771,0.0003420737,0.0003227377,0.0017462,0.0008243784,0.0009541623,0.009001925],"genre_scores_gemma":[0.4803271,0.0004444955,0.5114686,0.0002526985,0.0001413218,0.004702276,0.0009464609,0.0004831482,0.001233878],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2024872,"threshold_uncertainty_score":0.9834752,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2670104097609483,"score_gpt":0.4556427207423286,"score_spread":0.1886323109813803,"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."}}