{"id":"W2079234813","doi":"10.1111/j.0006-341x.2002.00209.x","title":"Interval Estimation for a Difference Between Intraclass Kappa Statistics","year":2002,"lang":"en","type":"article","venue":"Biometrics","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Statistics; Confidence interval; Cohen's kappa; Mathematics; Interval estimation; Kappa; Statistic; Sample size determination; Intraclass correlation; Reproducibility","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"],"consensus_categories":[],"category_scores_codex":[0.002863789,0.0001300698,0.0002579732,0.000938941,0.0001393758,0.0003218254,0.0006484619,0.00008446605,0.000353466],"category_scores_gemma":[0.01615218,0.000095891,0.00008377169,0.003177648,0.00008518841,0.0001359684,0.00008892419,0.00009148603,0.000359454],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001003356,"about_ca_system_score_gemma":0.0000153386,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008432401,"about_ca_topic_score_gemma":0.000003485761,"domain_scores_codex":[0.9968911,0.0001013549,0.0007154003,0.000390026,0.001642851,0.0002592664],"domain_scores_gemma":[0.9951007,0.003571343,0.0002495965,0.0004297738,0.000527841,0.0001207044],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006430146,0.0001370199,0.02443453,0.00002071175,0.0000147404,6.265117e-7,0.0001486627,0.00003575697,0.0001770106,0.001330446,0.03159675,0.9420973],"study_design_scores_gemma":[0.001672704,0.001356842,0.3019794,0.00005898427,0.0001106805,0.000002231893,0.0002880545,0.3562871,0.00173128,0.1739916,0.1617533,0.0007679071],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09006494,0.0001208995,0.9074925,0.0007320164,0.0005018935,0.0003744795,0.0003080836,0.00003074051,0.0003744372],"genre_scores_gemma":[0.9084426,0.00002447549,0.08995767,0.0001014242,0.000128353,0.00002741038,0.00002230548,0.000007736553,0.001287997],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9413294,"threshold_uncertainty_score":0.9921352,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4256073761305363,"score_gpt":0.418085093842297,"score_spread":0.007522282288239368,"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."}}