{"id":"W3213506774","doi":"10.1111/rssa.12696","title":"Combining Non-Probability and Probability Survey Samples Through Mass Imputation","year":2021,"lang":"en","type":"article","venue":"Journal of the Royal Statistical Society Series A (Statistics in Society)","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":57,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"National Science Foundation","keywords":"Statistics; Probability mass function; Imputation (statistics); Estimator; Mathematics; Probability sampling; Probability distribution; Conditional probability; Population; Survey sampling; Sample (material); Econometrics; Missing data; Demography","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":[],"consensus_categories":[],"category_scores_codex":[0.05634809,0.001005142,0.002654043,0.002818819,0.001002278,0.003182148,0.003492424,0.001821933,0.002962267],"category_scores_gemma":[0.1395271,0.0009468141,0.001759361,0.00488465,0.001605352,0.002913206,0.004149188,0.002323072,0.0007078956],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001118801,"about_ca_system_score_gemma":0.001251154,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003223506,"about_ca_topic_score_gemma":0.002645723,"domain_scores_codex":[0.9581997,0.0339025,0.001100581,0.002724573,0.00346798,0.0006045949],"domain_scores_gemma":[0.8832322,0.08914158,0.006954684,0.01512561,0.004971721,0.0005741713],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001264901,0.0008370519,0.1054105,0.0008121034,0.002568235,0.001548795,0.002642899,0.2376802,0.001399576,0.2744423,0.006778867,0.3646145],"study_design_scores_gemma":[0.000192107,0.0005172647,0.01828525,0.0002403021,0.0005025086,0.000307856,0.0004353219,0.6481192,0.001692782,0.3227662,0.006863767,0.00007741384],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04535054,0.0003082704,0.9514921,0.0004371185,0.00008355651,0.0004499749,0.0002953672,0.0001660893,0.001417034],"genre_scores_gemma":[0.5796529,0.0003735595,0.4149559,0.000364989,0.0002066797,0.001178136,0.001147983,0.00006430248,0.00205562],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.05634809,"threshold_uncertainty_score":0.2980008,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06967204401665635,"score_gpt":0.3486969212721688,"score_spread":0.2790248772555125,"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."}}