{"id":"W3032026822","doi":"10.1002/cjs.11551","title":"Correlated and misclassified binary observations in complex surveys","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Estimator; Generalized estimating equation; Binary data; Binary number; Gee; Computer science; Sampling (signal processing); Data mining; Focus (optics); Statistics; Survey data collection; Econometrics; Mathematics; Machine learning","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06334173,0.0008802539,0.001932166,0.002803179,0.00109347,0.002633796,0.003154696,0.002159239,0.001725685],"category_scores_gemma":[0.2105232,0.001179187,0.001672138,0.003822836,0.003544644,0.003029635,0.003177654,0.002425466,0.0003351529],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001836082,"about_ca_system_score_gemma":0.001531271,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004717666,"about_ca_topic_score_gemma":0.004239219,"domain_scores_codex":[0.956576,0.03034225,0.001957052,0.006457472,0.004001756,0.0006655466],"domain_scores_gemma":[0.7608643,0.1906179,0.02590599,0.01780428,0.004037352,0.0007701366],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0005583164,0.0002637987,0.1914719,0.001330782,0.001145604,0.001810865,0.004052169,0.2157138,0.001325624,0.3353824,0.004443768,0.2425011],"study_design_scores_gemma":[0.0001078206,0.000212289,0.05295298,0.000674639,0.0003817829,0.001055229,0.0008538293,0.5403022,0.001881532,0.3943955,0.007037875,0.0001444509],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08400597,0.001486598,0.9121482,0.0006964838,0.0001086433,0.00017914,0.0002668303,0.0001738066,0.0009342178],"genre_scores_gemma":[0.7190569,0.001813478,0.274431,0.0007394727,0.0001925834,0.0007410495,0.0008700758,0.00008406938,0.002071196],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.06334173,"threshold_uncertainty_score":0.334987,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2547201797386306,"score_gpt":0.3368134296065589,"score_spread":0.08209324986792821,"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."}}