{"id":"W1979334793","doi":"10.1111/1467-9884.00266","title":"Statistical Inferences For Interobserver Agreement Studies With Nominal Outcome Data","year":2001,"lang":"en","type":"article","venue":"Journal of the Royal Statistical Society Series D (The Statistician)","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University; Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Categorical variable; Outcome (game theory); Statistical inference; Statistics; Econometrics; Statistical hypothesis testing; Nominal level; Inference; Multiple comparisons problem; Focus (optics); Computer science; Mathematics; Artificial intelligence; Confidence interval","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008997114,0.000399809,0.0009420199,0.00003744577,0.0009424218,0.0005482832,0.00329156,0.00008562523,0.001013641],"category_scores_gemma":[0.01623049,0.0001687901,0.0002835518,0.0004001642,0.001735616,0.0004540808,0.000842089,0.0006180723,0.00004309736],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002618697,"about_ca_system_score_gemma":0.0002919378,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007731915,"about_ca_topic_score_gemma":0.0006640728,"domain_scores_codex":[0.9923142,0.0007281729,0.002314333,0.0005982415,0.003406787,0.0006382595],"domain_scores_gemma":[0.9846421,0.01073516,0.001373992,0.001242017,0.001762576,0.000244163],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.003308753,0.000911653,0.1104339,0.0002826021,0.002517648,0.00009939782,0.004506975,0.00471128,0.00002500853,0.1008661,0.6893908,0.08294585],"study_design_scores_gemma":[0.00391501,0.005149884,0.3240359,0.0004043086,0.001825108,0.0001593195,0.03618169,0.02521204,0.00003061855,0.3355081,0.2665102,0.001067854],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02137651,0.0003438235,0.9576968,0.01567687,0.001660285,0.0008460031,0.002153522,0.00001273584,0.0002334212],"genre_scores_gemma":[0.7271053,0.0001715526,0.2652214,0.002675688,0.0009216703,0.00005428626,0.00004961726,0.00004569533,0.003754831],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7057287,"threshold_uncertainty_score":0.9998996,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3584683688179907,"score_gpt":0.4458766577488586,"score_spread":0.08740828893086794,"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."}}