{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3470378,0.0002609011,0.001126708,0.0003171687,0.000635898,0.0002511844,0.003297167,0.000447857,0.0008096859],"category_scores_gemma":[0.8918822,0.0001864536,0.0003135111,0.001076753,0.0008022512,0.0003499154,0.001207392,0.0007865009,0.00004570411],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001853395,"about_ca_system_score_gemma":0.002523184,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002758091,"about_ca_topic_score_gemma":0.0003406374,"domain_scores_codex":[0.9347641,0.05104046,0.002333362,0.002412321,0.008000678,0.001449097],"domain_scores_gemma":[0.4472745,0.5396779,0.0008955213,0.003221999,0.006813199,0.002116955],"domain_codex":null,"domain_gemma":"methods","domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.009065401,0.0005422449,0.002173008,0.0003620243,0.0003355102,0.00001661116,0.001600174,0.0005165896,0.0571048,0.005255338,0.1233234,0.7997049],"study_design_scores_gemma":[0.003950355,0.001112296,0.00008803976,0.00005651392,0.00006757223,0.000008103986,0.002799793,0.2378906,0.004435614,0.03224042,0.7170838,0.0002669609],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002484589,0.0004510766,0.9788967,0.01254353,0.002125253,0.003102865,0.0001233271,0.00005018777,0.0002224705],"genre_scores_gemma":[0.005849201,0.00007368642,0.9896866,0.001105719,0.002447798,0.00047534,0.00008486683,0.00002762176,0.0002491588],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7994379,"threshold_uncertainty_score":0.8865492,"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."}}