{"id":"W4411763865","doi":"10.1093/aje/kwaf132","title":"A two-step approach to simultaneously correct for selection and misclassification bias in nonprobability samples from hard-to-reach populations","year":2025,"lang":"en","type":"article","venue":"American Journal of Epidemiology","topic":"Census and Population Estimation","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University; Institute for Work & Health; BC Centre for Disease Control; Public Health Ontario; University of Toronto","funders":"","keywords":"Selection bias; Statistics; Sampling bias; Sample (material); Population; Nonprobability sampling; Sampling (signal processing); Computer science; Estimator; Selection (genetic algorithm); Sample size determination; Econometrics; Mathematics; Machine learning; Medicine; Environmental health","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":[],"category_scores_codex":[0.0326383,0.001202059,0.001829876,0.002793791,0.001189691,0.00176635,0.003112488,0.002304911,0.002827011],"category_scores_gemma":[0.09598648,0.0008693405,0.002044693,0.002180331,0.001084457,0.001889632,0.003654969,0.002464764,0.000731753],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007361605,"about_ca_system_score_gemma":0.003435737,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002562521,"about_ca_topic_score_gemma":0.004544517,"domain_scores_codex":[0.9778536,0.01451867,0.00117895,0.002266058,0.003830823,0.000351867],"domain_scores_gemma":[0.9566451,0.02935089,0.002963229,0.004958406,0.005541798,0.0005405139],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008614535,0.00122218,0.07484077,0.001095873,0.001971488,0.0006259964,0.002121321,0.03353329,0.008485703,0.0471805,0.005062891,0.8229986],"study_design_scores_gemma":[0.0004914147,0.001863226,0.05257818,0.0004896048,0.001123498,0.0017636,0.0007426749,0.8149077,0.01891266,0.08683722,0.019978,0.0003122125],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01034641,0.0001534464,0.9878619,0.0003060724,0.00008226145,0.0005813365,0.00007640143,0.0002120247,0.0003801292],"genre_scores_gemma":[0.09826746,0.0001613809,0.8974273,0.0004797416,0.00007966216,0.001414892,0.0002618878,0.00006606303,0.001841691],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9673617,"threshold_uncertainty_score":0.1726099,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2383315004023227,"score_gpt":0.4254556089763714,"score_spread":0.1871241085740487,"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."}}