{"id":"W3035592618","doi":"10.1186/s12874-020-01022-x","title":"Using multiple agreement methods for continuous repeated measures data: a tutorial for practitioners","year":2020,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":88,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Emory University","keywords":"Concordance; Cohen's kappa; Computer science; Concordance correlation coefficient; Data mining; Statistics; Strengths and weaknesses; Correlation coefficient; Pulmonary disease; Limits of agreement; Medical physics; Medicine; Mathematics; Machine learning; Psychology","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":[0.1127555,0.005298162,0.003411827,0.01117061,0.001516849,0.00537741,0.007489451,0.007449409,0.02740369],"category_scores_gemma":[0.3081675,0.003898024,0.005118295,0.00689824,0.005349374,0.01125236,0.004451348,0.01513,0.02267841],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002690501,"about_ca_system_score_gemma":0.005410047,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002319067,"about_ca_topic_score_gemma":0.003040342,"domain_scores_codex":[0.9147992,0.060495,0.009523525,0.002798112,0.01182273,0.0005614527],"domain_scores_gemma":[0.5427142,0.4043837,0.009474179,0.0112366,0.03030152,0.001889738],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001909828,0.0003208034,0.001267667,0.01291967,0.0004461607,0.0008374805,0.005272673,0.003483378,0.002504589,0.05131692,0.3853798,0.5360599],"study_design_scores_gemma":[0.0002116449,0.0003869919,0.001966381,0.0145977,0.0001651115,0.003003834,0.001909227,0.01234895,0.002034667,0.1909147,0.771984,0.0004768965],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003064985,0.02022635,0.9498793,0.01327117,0.00375168,0.001683465,0.0008970306,0.004437332,0.005546991],"genre_scores_gemma":[0.002778684,0.01586731,0.9657905,0.003992304,0.002378706,0.004652568,0.0004630288,0.001715393,0.002361503],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1127555,"threshold_uncertainty_score":0.5963151,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9644013985579888,"score_gpt":0.7181859517571121,"score_spread":0.2462154468008767,"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."}}