{"id":"W2153012086","doi":"10.1111/j.1524-4733.2009.00602.x","title":"Good Research Practices for Comparative Effectiveness Research: Analytic Methods to Improve Causal Inference from Nonrandomized Studies of Treatment Effects Using Secondary Data Sources: The ISPOR Good Research Practices for Retrospective Database Analysis Task Force Report—Part III","year":2009,"lang":"en","type":"article","venue":"Value in Health","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":290,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Causal inference; Inference; Confounding; Statistical inference; Comparative effectiveness research; Marginal structural model; Medicine; Propensity score matching; Instrumental variable; Outcomes research; Research design; Computer science; Econometrics; Management science; Statistics; Machine learning; Alternative medicine; Artificial intelligence; Engineering; Mathematics","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","metaepi_narrow","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1245983,0.0005535864,0.003031022,0.001754285,0.001352667,0.000223041,0.001507659,0.0002329345,0.000007585712],"category_scores_gemma":[0.1799678,0.0003951015,0.0002597456,0.004778909,0.0007757317,0.001311521,0.0008061209,0.001769928,0.000001245777],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003183897,"about_ca_system_score_gemma":0.003212451,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03160303,"about_ca_topic_score_gemma":0.006446623,"domain_scores_codex":[0.9639859,0.02752245,0.002314429,0.002406283,0.001956847,0.001814108],"domain_scores_gemma":[0.7062866,0.2812821,0.003860109,0.003866755,0.004351499,0.0003529797],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.1650445,0.02365979,0.01271477,0.029129,0.0500786,0.0006806336,0.2395029,0.02155088,0.2460101,0.1605324,0.005384399,0.04571204],"study_design_scores_gemma":[0.02234323,0.03279747,0.002180052,0.006125017,0.00361243,0.00002829648,0.05708302,0.1836645,0.1302502,0.5580377,0.002362563,0.001515511],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5135121,0.004568731,0.4429642,0.001916256,0.0002416289,0.03379567,0.002607129,0.0001584062,0.0002359378],"genre_scores_gemma":[0.6271013,0.000572785,0.3682908,0.0000378282,0.0002534191,0.003173406,0.0003552945,0.00006411018,0.0001509833],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3975053,"threshold_uncertainty_score":0.9999474,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8166517374954501,"score_gpt":0.7018213479349174,"score_spread":0.1148303895605327,"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."}}