{"id":"W1990424977","doi":"10.1007/s00180-013-0424-7","title":"Evaluation of confidence intervals for the kappa statistic when the assumption of marginal homogeneity is violated","year":2013,"lang":"en","type":"article","venue":"Computational Statistics","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University; McMaster University; Ontario Clinical Oncology Group","funders":"","keywords":"Homogeneity (statistics); Kappa; Statistic; Confidence interval; Statistics; Mathematics; Cohen's kappa; Econometrics; Test statistic; Statistical hypothesis testing","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01108366,0.000108889,0.0002079941,0.00005836607,0.0001833954,0.0001100708,0.0005753491,0.00003487771,0.001911438],"category_scores_gemma":[0.006603666,0.00005991559,0.00007301322,0.0001985109,0.000296625,0.000123742,0.00006383814,0.00007974653,0.00005884788],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006735007,"about_ca_system_score_gemma":0.0002297441,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001775019,"about_ca_topic_score_gemma":0.00003715284,"domain_scores_codex":[0.9945778,0.0006517194,0.0009604007,0.0002433813,0.003427859,0.0001388002],"domain_scores_gemma":[0.9819694,0.009931479,0.0006902279,0.0003355812,0.007037858,0.00003548508],"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":[0.00009285208,0.0002808275,0.007044494,0.00008839821,0.0002946211,1.520364e-7,0.003219317,0.3627656,0.0006701977,0.07843429,0.1131222,0.433987],"study_design_scores_gemma":[0.0002197618,0.00006397018,0.1304248,0.00001492511,0.0000813108,4.511114e-7,0.0001949497,0.4158411,0.0001103638,0.4528456,0.000163859,0.00003893363],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04990353,0.0001964945,0.9459013,0.001601491,0.0002415202,0.001234042,0.0008566742,0.000004362234,0.00006063285],"genre_scores_gemma":[0.9513144,0.000009056163,0.04826121,0.000167719,0.00003020129,0.000101579,0.00004931566,0.000005000416,0.00006152449],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9014109,"threshold_uncertainty_score":0.999001,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3043425736713799,"score_gpt":0.4321275538967644,"score_spread":0.1277849802253845,"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."}}