{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07155238,0.001684424,0.002640531,0.01015776,0.001227233,0.003590522,0.004322316,0.002896364,0.004625821],"category_scores_gemma":[0.3717094,0.0008260179,0.002631608,0.004594629,0.002432992,0.004701082,0.004542513,0.005026207,0.001681692],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001090178,"about_ca_system_score_gemma":0.00162566,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000826223,"about_ca_topic_score_gemma":0.0005720568,"domain_scores_codex":[0.9028804,0.05897373,0.006320077,0.009172386,0.02153203,0.001121408],"domain_scores_gemma":[0.6689631,0.2766858,0.01346639,0.01936478,0.02043458,0.001085329],"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":[0.00194195,0.000349776,0.02036106,0.003044674,0.001988284,0.0004114165,0.002755391,0.0326596,0.007779424,0.168248,0.01080405,0.7496563],"study_design_scores_gemma":[0.000782556,0.003058058,0.05143866,0.002593399,0.001510109,0.0038525,0.001560871,0.3658221,0.02132258,0.5055968,0.04139427,0.001068118],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005624362,0.001034147,0.9903058,0.0001412949,0.0001664364,0.0001860576,0.0001756191,0.0006372098,0.001729031],"genre_scores_gemma":[0.1373969,0.000726314,0.8586091,0.0001877135,0.0002108737,0.001428156,0.000518573,0.0003891254,0.0005332498],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.07155238,"threshold_uncertainty_score":0.3784097,"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."}}