{"id":"W2124916392","doi":"10.1093/ije/dyn147","title":"Size matters: just how big is BIG?: Quantifying realistic sample size requirements for human genome epidemiology","year":2008,"lang":"en","type":"article","venue":"International Journal of Epidemiology","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":261,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; The Quebec Population Health Research Network","funders":"Northwest Regional Development Agency; Wellcome Trust","keywords":"Sample size determination; Biobank; Sample (material); Computer science; Variety (cybernetics); Replicate; Data science; Risk analysis (engineering); Biology; Business; Statistics; Bioinformatics; Mathematics; Artificial intelligence","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":[0.2320389,0.001114371,0.001626094,0.001868083,0.001269098,0.004902676,0.002896618,0.004774916,0.002303297],"category_scores_gemma":[0.6749616,0.0009097435,0.00139668,0.00221548,0.008304453,0.008185045,0.005734119,0.004211911,0.0004515196],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00248194,"about_ca_system_score_gemma":0.004629764,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001653231,"about_ca_topic_score_gemma":0.001113295,"domain_scores_codex":[0.7070271,0.2660386,0.005424538,0.006327054,0.01404729,0.001135476],"domain_scores_gemma":[0.2295627,0.7332121,0.01302462,0.01752336,0.00533451,0.00134276],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001041449,0.0002123501,0.05984114,0.003016991,0.001277201,0.0006677696,0.005561222,0.094639,0.001922715,0.6252311,0.01227857,0.1943105],"study_design_scores_gemma":[0.000240531,0.0006688697,0.01473052,0.001393671,0.0002864221,0.000779229,0.0007801056,0.08735846,0.001707494,0.8786575,0.0132802,0.0001169909],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02870213,0.004743766,0.9372419,0.01922884,0.0005506059,0.001307947,0.000603952,0.0001919833,0.007428913],"genre_scores_gemma":[0.5881698,0.00201741,0.3996687,0.004416846,0.0006542624,0.004010921,0.0004059962,0.0001807683,0.0004753353],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7679611,"threshold_uncertainty_score":0.9470328,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2458817182645014,"score_gpt":0.4137981801648385,"score_spread":0.1679164619003371,"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."}}