{"id":"W4362636314","doi":"10.1177/1536867x231161978","title":"Extended biasplot command to assess bias, precision, and agreement in method comparison studies","year":2023,"lang":"en","type":"article","venue":"The Stata Journal Promoting communications on statistics and Stata","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Statistics; Computer science; Limits of agreement; Accuracy and precision; Data mining; Mathematics; Nuclear medicine; Medicine","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":["metaresearch"],"category_scores_codex":[0.03210633,0.0002326891,0.0005296866,0.0004745875,0.00158739,0.0008534907,0.001926187,0.00003679769,0.0000200374],"category_scores_gemma":[0.01159693,0.0001423396,0.00003851408,0.001092348,0.0003012477,0.0001915985,0.001696773,0.0006847375,0.00004360394],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001107587,"about_ca_system_score_gemma":0.00007938226,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005931568,"about_ca_topic_score_gemma":0.0003918984,"domain_scores_codex":[0.9929107,0.003031416,0.001574851,0.0004481004,0.001629408,0.0004054655],"domain_scores_gemma":[0.9803253,0.0162194,0.0005768546,0.001927694,0.0007368457,0.000213958],"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":[0.0002218873,0.0006836731,0.01766889,0.0000910969,0.0002499724,0.00002778284,0.03665916,0.002009287,0.0002446634,0.04566475,0.07490741,0.8215714],"study_design_scores_gemma":[0.00250304,0.001871654,0.1933587,0.001191663,0.0001643722,0.00007568775,0.1173106,0.2688134,0.0001709505,0.3535877,0.06012063,0.0008315455],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.511878,0.005431054,0.4156828,0.05961649,0.0008517563,0.003253567,0.001890371,0.0001412388,0.00125474],"genre_scores_gemma":[0.8281842,0.00560847,0.1653966,0.0003834131,0.00003846412,0.0000578263,0.00003810112,0.00002440761,0.0002685657],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8207399,"threshold_uncertainty_score":0.9997124,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6821565065636919,"score_gpt":0.5640156980598392,"score_spread":0.1181408085038527,"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."}}