{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003383002,0.000368472,0.0009486335,0.00001120547,0.0003858934,0.0002224319,0.0003683403,0.000259997,0.0001631377],"category_scores_gemma":[0.01512456,0.0002762378,0.0003239176,0.0004878547,0.001130999,0.0001967912,0.0002919162,0.001079312,0.000001075311],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003505349,"about_ca_system_score_gemma":0.0005279452,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001578316,"about_ca_topic_score_gemma":0.0002201215,"domain_scores_codex":[0.9954881,0.00113853,0.001524048,0.0004627725,0.0008256063,0.0005609262],"domain_scores_gemma":[0.9855264,0.0121318,0.0007344807,0.0003970388,0.00100884,0.0002014658],"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":[0.0001599636,0.0004859883,0.04465939,0.001187094,0.0003058792,0.00004378721,0.003920261,0.0001354745,0.000125214,0.9265967,0.0152716,0.007108622],"study_design_scores_gemma":[0.000789769,0.0001686481,0.09842663,0.0001500232,0.0001315059,0.00003050064,0.0009925357,0.006939448,0.0001175532,0.8917933,0.0001775078,0.00028259],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01870634,0.0001270278,0.9782921,0.0005067988,0.000445463,0.000313071,0.001452608,0.0000165225,0.0001400778],"genre_scores_gemma":[0.05404974,0.0001528616,0.9452976,0.0002587744,0.00009262288,0.00001156457,0.00002478133,0.00003698493,0.00007506798],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.05376725,"threshold_uncertainty_score":0.999969,"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."}}