{"id":"W2613103431","doi":"10.1177/0962280217702540","title":"Comparing heteroscedastic measurement systems with the probability of agreement","year":2017,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"Actua; University of Waterloo","funders":"","keywords":"Homoscedasticity; Heteroscedasticity; Metric (unit); Observational error; Computer science; Statistics; Mathematics; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2066495,0.001893912,0.00303221,0.0106235,0.001912191,0.008773235,0.003297288,0.003462369,0.002825965],"category_scores_gemma":[0.5395287,0.001062065,0.003942202,0.01152285,0.01223296,0.01120321,0.008238774,0.004482199,0.0007274204],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002316521,"about_ca_system_score_gemma":0.002580959,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001507272,"about_ca_topic_score_gemma":0.0007778525,"domain_scores_codex":[0.7349167,0.1872914,0.0172617,0.02398413,0.03497139,0.001574713],"domain_scores_gemma":[0.2374082,0.6774237,0.03746408,0.02909127,0.01749667,0.001116174],"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":[0.001924519,0.000291598,0.1742056,0.003397855,0.009898282,0.0005258374,0.009593252,0.08821746,0.002681627,0.3202258,0.004273016,0.3847651],"study_design_scores_gemma":[0.0001839464,0.001406819,0.08341926,0.0009169516,0.001387499,0.0008235366,0.002519551,0.2504672,0.004130519,0.6438896,0.01026745,0.0005876338],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04436892,0.002590047,0.9457011,0.0008548892,0.0003645409,0.0004630456,0.0005032766,0.0003377474,0.00481646],"genre_scores_gemma":[0.7000275,0.001140987,0.2946566,0.0003569886,0.0004743256,0.001770345,0.0006891425,0.0001986973,0.0006855425],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2066495,"threshold_uncertainty_score":0.9783424,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7493861067260326,"score_gpt":0.6289003428450651,"score_spread":0.1204857638809674,"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."}}