{"id":"W1980472079","doi":"10.1136/bmj.c117","title":"Is a subgroup effect believable? Updating criteria to evaluate the credibility of subgroup analyses","year":2010,"lang":"en","type":"article","venue":"BMJ","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":812,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Subgroup analysis; Credibility; Psychology; Computer science; Information retrieval; Mathematics; Statistics; Political science","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7639732,0.003559431,0.009758552,0.01837479,0.006711408,0.01362848,0.01340871,0.01559088,0.003698401],"category_scores_gemma":[0.9515347,0.003588847,0.01241935,0.008588603,0.02177141,0.0201908,0.01524167,0.02763853,0.0008192366],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.007495451,"about_ca_system_score_gemma":0.01157802,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004499687,"about_ca_topic_score_gemma":0.003797256,"domain_scores_codex":[0.1970384,0.5867434,0.1134353,0.01565398,0.08430521,0.002823787],"domain_scores_gemma":[0.01982957,0.8837875,0.0265731,0.03773469,0.03040128,0.001673789],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.01295887,0.0007134472,0.1010499,0.02016523,0.03046883,0.002262407,0.04502948,0.01467919,0.003032966,0.1579844,0.04108193,0.5705733],"study_design_scores_gemma":[0.005087446,0.002983528,0.02595461,0.02437279,0.01538313,0.003384233,0.006683235,0.1162026,0.01021376,0.7343088,0.05357157,0.001854188],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07414968,0.01638149,0.7961951,0.08433396,0.008638511,0.00721765,0.001308399,0.001192969,0.01058223],"genre_scores_gemma":[0.4443515,0.001680666,0.5304815,0.01302778,0.002807699,0.006045862,0.0005289202,0.0004559538,0.0006200534],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2360268,"threshold_uncertainty_score":0.2910631,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5243444902286908,"score_gpt":0.5884504748589897,"score_spread":0.06410598463029893,"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."}}