{"id":"W2007345088","doi":"10.1371/journal.pone.0073990","title":"The Case for Using the Repeatability Coefficient When Calculating Test–Retest Reliability","year":2013,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":474,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Curtin University of Technology","keywords":"Intraclass correlation; Repeatability; Reliability (semiconductor); Strengths and weaknesses; Computer science; Pearson product-moment correlation coefficient; Statistics; Test (biology); Measure (data warehouse); Reliability engineering; Correlation coefficient; Data mining; Medical physics; Machine learning; Mathematics; Reproducibility; Medicine; Psychology; Engineering","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":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.01775398,0.0002072145,0.0003321327,0.0000356502,0.001985018,0.000793622,0.00102685,0.00007934347,0.000290215],"category_scores_gemma":[0.06078167,0.0000963998,0.0002036914,0.0004053282,0.0004938233,0.0002770914,0.000315456,0.0002649582,0.00009350516],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002070842,"about_ca_system_score_gemma":0.00009606268,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005538755,"about_ca_topic_score_gemma":0.0001701672,"domain_scores_codex":[0.9948629,0.0006426198,0.001220265,0.0007740533,0.001976232,0.0005239233],"domain_scores_gemma":[0.9732891,0.02082653,0.0004852084,0.002953324,0.002271377,0.0001744721],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003539921,0.0180725,0.781798,0.0006240397,0.0005908543,0.00005420441,0.009725716,0.01553076,0.06705296,0.004561966,0.01762033,0.08401469],"study_design_scores_gemma":[0.0008324501,0.0005734155,0.01553934,0.0001776564,0.0002609665,0.00003672189,0.006709621,0.8500034,0.01109514,0.1113677,0.002813156,0.0005904653],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9828515,0.0001199228,0.005306322,0.008109681,0.0001549659,0.002943767,0.00003138279,0.00004853826,0.0004339385],"genre_scores_gemma":[0.9882015,0.000002757638,0.01070322,0.0002668677,0.0001405079,0.0002682327,0.000001706097,0.00001289647,0.0004023364],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8344726,"threshold_uncertainty_score":0.9993142,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2965950402626327,"score_gpt":0.3528709709396792,"score_spread":0.0562759306770465,"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."}}