{"id":"W2891506233","doi":"10.1177/0962280218799540","title":"A review and empirical comparison of causal inference methods for clustered observational data with application to the evaluation of the effectiveness of medical devices","year":2018,"lang":"en","type":"review","venue":"Statistical Methods in Medical Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Toronto","funders":"","keywords":"Observational study; Causal inference; Propensity score matching; Confounding; Matching (statistics); Cluster analysis; Metric (unit); Variance (accounting); Computer science; Statistics; Econometrics; Inference; Cluster (spacecraft); Data mining; Medicine; Mathematics; Artificial intelligence; Engineering; Operations management","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":[0.1976474,0.0003105349,0.002684845,0.0002011622,0.00008622992,0.00001427959,0.002834834,0.0005506336,0.0001411704],"category_scores_gemma":[0.4823495,0.0001544482,0.00008946415,0.001635859,0.002156086,0.00006810754,0.001917685,0.001492029,5.868196e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000176149,"about_ca_system_score_gemma":0.003672902,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007506337,"about_ca_topic_score_gemma":0.0002312227,"domain_scores_codex":[0.931025,0.05828843,0.002895758,0.001039436,0.006206573,0.0005447578],"domain_scores_gemma":[0.6632987,0.33008,0.00101504,0.002211086,0.003055612,0.0003395433],"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":[0.00006646064,0.0001681274,0.00005229777,0.07362717,0.00008485366,1.837361e-7,0.0000523267,2.519608e-7,0.000001757759,0.04547108,0.0005554103,0.8799201],"study_design_scores_gemma":[0.0009388491,0.001299932,0.0009468764,0.2125624,0.00303474,0.00002005597,0.00009957981,0.05065166,0.0001282076,0.5662104,0.163595,0.0005121856],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000002053228,0.3403773,0.6541597,0.0004082025,0.00002797764,0.004773888,0.0002112517,0.000007176955,0.0000324898],"genre_scores_gemma":[0.00004169108,0.2906206,0.707092,0.00005124931,0.00003932308,0.002020675,0.0001034708,0.00002973031,0.000001298417],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8794079,"threshold_uncertainty_score":0.8261908,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.885421416171426,"score_gpt":0.8016456215590271,"score_spread":0.08377579461239892,"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."}}