{"id":"W2262143275","doi":"10.1093/aje/kwv152","title":"The Impact of Sparse Follow-up on Marginal Structural Models for Time-to-Event Data","year":2015,"lang":"en","type":"review","venue":"American Journal of Epidemiology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Université de Montréal; Health Canada; Centre Hospitalier Universitaire de Québec; Canadian Institutes of Health Research; University of Ottawa; McGill University; Institute for Clinical Evaluative Sciences; McGill University Health Centre; McMaster University; Ottawa Hospital Research Institute; Natural Sciences and Engineering Research Council of Canada; Faculty of Medicine, McGill University","keywords":"Missing data; Covariate; Hazard ratio; Statistics; Confounding; Marginal structural model; Medicine; Imputation (statistics); Confidence interval; Proportional hazards model; Event (particle physics); Econometrics; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.009139792,0.0005499966,0.005477034,0.0002629228,0.0000666394,0.000008521361,0.002228151,0.0001861715,0.00003801757],"category_scores_gemma":[0.0192182,0.0002788093,0.001123211,0.0002649935,0.0005294699,0.0001517005,0.0003465122,0.0007977989,0.00001167419],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004633561,"about_ca_system_score_gemma":0.0009010091,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004533225,"about_ca_topic_score_gemma":0.000003578257,"domain_scores_codex":[0.994046,0.001965996,0.002704953,0.0003961154,0.0002468621,0.0006400268],"domain_scores_gemma":[0.9705489,0.02018656,0.006869353,0.001530221,0.0005334385,0.000331562],"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":[0.0003056613,0.00002741596,0.000002982878,0.000314454,0.0007105618,0.000005319444,0.00002748439,0.0004313392,4.607239e-7,0.008328347,0.05496251,0.9348835],"study_design_scores_gemma":[0.0003260727,0.006946135,0.000002147901,0.004011683,0.001009828,0.0005161324,0.00003758067,0.002168453,5.356762e-7,0.5687595,0.4157759,0.0004460547],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00009691592,0.8025415,0.1937098,0.0003627031,0.0003530149,0.001672709,0.0009824763,0.00004291206,0.0002379995],"genre_scores_gemma":[0.0001174297,0.8468226,0.1520757,0.0001001149,0.0004242795,0.00004650471,0.00008513559,0.0001146147,0.0002136216],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9344374,"threshold_uncertainty_score":0.9999664,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4973999321594651,"score_gpt":0.5646419536567407,"score_spread":0.06724202149727565,"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."}}