{"id":"W3181769638","doi":"10.1186/s12874-021-01332-8","title":"Survey design and analysis considerations when utilizing misclassified sampling strata","year":2021,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Public Health Ontario; University of Toronto","funders":"National Human Genome Research Institute; National Heart, Lung, and Blood Institute","keywords":"Stratified sampling; Sampling design; Sampling (signal processing); Simple random sample; Statistics; Systematic sampling; Sample size determination; Sample (material); Inference; Survey sampling; Computer science; Econometrics; Mathematics; Medicine; Artificial intelligence; Environmental health; Population","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","sts","insufficient_payload"],"consensus_categories":["metaresearch","sts"],"category_scores_codex":[0.5323557,0.0001497404,0.0007313291,0.0005472784,0.001470612,0.0001337835,0.0003735698,0.0006980335,0.007502187],"category_scores_gemma":[0.8733763,0.00013881,0.000131587,0.001756898,0.002792387,0.0001090472,0.0003021614,0.0011179,0.00002135788],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007137367,"about_ca_system_score_gemma":0.00781981,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003854489,"about_ca_topic_score_gemma":0.1085116,"domain_scores_codex":[0.4476766,0.5487708,0.0005015497,0.0007336057,0.001389418,0.0009280196],"domain_scores_gemma":[0.3034618,0.6943706,0.00007480809,0.0004215875,0.000901154,0.0007700241],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00932559,0.0007448678,0.5236855,0.0001833775,0.003948173,0.001510219,0.04668747,0.0002520651,0.007963184,0.2907092,0.01375913,0.1012312],"study_design_scores_gemma":[0.001019444,0.000142534,0.8810716,0.00004803475,0.0002555115,0.00003395789,0.01742479,0.00287152,0.001406064,0.08935367,0.005940913,0.0004319909],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07893009,0.001933992,0.9132447,0.00373094,0.0002971138,0.0002445521,0.0000251056,0.00005281798,0.001540712],"genre_scores_gemma":[0.1351427,0.0009978547,0.861333,0.0005967821,0.0002369412,0.00005776645,0.00006844368,0.00001880703,0.001547731],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3573861,"threshold_uncertainty_score":0.9999214,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9413660578017012,"score_gpt":0.6646432639260955,"score_spread":0.2767227938756057,"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."}}