{"id":"W4410784164","doi":"10.1186/s12874-025-02594-2","title":"Comparison of methods to handle missing values in a continuous index test in a diagnostic accuracy study – a simulation study","year":2025,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Universitätsklinikum Hamburg-Eppendorf; Deutsche Forschungsgemeinschaft","keywords":"Missing data; Statistics; Covariate; Imputation (statistics); Sample size determination; Inverse probability weighting; Weighting; Correlation; Mathematics; Medicine; Estimator","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"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08979559,0.0002255853,0.001748348,0.001380428,0.00009895935,0.00004361089,0.0007084263,0.0002798525,0.0002280513],"category_scores_gemma":[0.9366587,0.0001879281,0.00006554797,0.002438724,0.0003571607,0.00005470384,0.0006543457,0.001290386,0.000003983588],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001565621,"about_ca_system_score_gemma":0.0009849728,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0015067,"about_ca_topic_score_gemma":0.004062698,"domain_scores_codex":[0.9175276,0.07635962,0.002582313,0.0009251413,0.001600378,0.001005004],"domain_scores_gemma":[0.1991512,0.7992402,0.0002093381,0.0006156834,0.0004611523,0.0003224357],"domain_codex":null,"domain_gemma":"methods","domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003836686,0.006122018,0.6494406,0.0002848371,0.00002995675,0.00006131909,0.006400825,0.00007303779,0.0001956215,0.004954449,0.00006507392,0.3319886],"study_design_scores_gemma":[0.00322917,0.002536908,0.4465387,0.0008884256,0.0000461632,0.000001631049,0.01767781,0.086499,0.0003562534,0.4419898,0.00003459156,0.0002016015],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2802536,0.0001079459,0.717057,0.0001924944,0.000103616,0.002081278,0.000002701287,0.00001953716,0.0001818507],"genre_scores_gemma":[0.5030883,0.000003500678,0.4966041,0.00002551186,0.00002166232,0.0002250324,4.142487e-7,0.00001081269,0.00002067276],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8468632,"threshold_uncertainty_score":0.937247,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6339960035583913,"score_gpt":0.6978124382894738,"score_spread":0.06381643473108256,"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."}}