{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002574952,0.0001342635,0.0006671207,0.0003256113,0.00008263258,0.00001028005,0.0001047591,0.00006102092,0.000005421541],"category_scores_gemma":[0.02121878,0.0001176443,0.00008836623,0.0004929613,0.00006182507,0.00006122926,0.00001955774,0.0001638489,9.612361e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001931676,"about_ca_system_score_gemma":0.00006937738,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001844848,"about_ca_topic_score_gemma":0.001377678,"domain_scores_codex":[0.997628,0.0007237728,0.001095137,0.0002682547,0.00007547934,0.000209305],"domain_scores_gemma":[0.9917468,0.006991533,0.0007011489,0.0001695363,0.0002787198,0.0001122188],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0006434814,0.0003079869,0.7603544,0.00005204405,0.00008049844,3.748079e-7,0.000953601,0.05857026,0.0006073616,0.06436965,0.003901534,0.1101588],"study_design_scores_gemma":[0.0008700201,0.0005289803,0.606292,0.0001120595,0.0001323704,0.00003446161,0.000519337,0.2346392,0.00002371063,0.1536458,0.00297885,0.0002232861],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4859421,0.00002290615,0.5112301,0.0022965,0.0001024948,0.0003248419,0.00001761336,0.00001006261,0.00005343703],"genre_scores_gemma":[0.5731627,0.000002554447,0.4262991,0.0004104295,0.00005252452,0.00002329923,0.00002417879,0.00000684556,0.00001835734],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1760689,"threshold_uncertainty_score":0.9870259,"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."}}