{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.005358798,0.0003562244,0.001172095,0.0001863748,0.0003018876,0.00001385684,0.0009467112,0.0005223503,0.0001043268],"category_scores_gemma":[0.07265161,0.0003218971,0.0006617095,0.00009207069,0.0005099403,0.00001403018,0.0002200914,0.0003202941,0.000009657308],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001593702,"about_ca_system_score_gemma":0.00024539,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002684411,"about_ca_topic_score_gemma":0.00008983846,"domain_scores_codex":[0.9950788,0.001280913,0.00203801,0.0006169721,0.0001954966,0.0007898033],"domain_scores_gemma":[0.9860694,0.009792653,0.002410307,0.0004424337,0.00103388,0.0002513485],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001031928,0.0004667706,0.5922992,0.00008183336,0.003568245,0.00007297315,0.0004779309,0.001524615,0.156003,0.003932845,0.2321867,0.008354006],"study_design_scores_gemma":[0.004654682,0.00231284,0.4991614,0.0001052078,0.0002569483,0.001533527,0.0003417984,0.0003282268,0.001006768,0.04098864,0.4483844,0.0009255763],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7302214,0.002507628,0.1916188,0.06903649,0.00533356,0.0004490951,0.000622256,0.00002219833,0.0001885476],"genre_scores_gemma":[0.9106637,0.002067687,0.05698983,0.0253814,0.003826384,0.0000402883,0.0002810805,0.00005169159,0.0006978967],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2161977,"threshold_uncertainty_score":0.9999233,"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."}}