{"id":"W2906823368","doi":"10.48550/arxiv.1812.10694","title":"Combining Non-probability and Probability Survey Samples Through Mass Imputation","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Imputation (statistics); Estimator; Statistics; Mathematics; Probability mass function; Probability sampling; Consistency (knowledge bases); Econometrics; Probability distribution; Missing data; Discrete mathematics; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04433987,0.001226429,0.002953425,0.00309023,0.00106771,0.003113335,0.004982553,0.002527561,0.004817537],"category_scores_gemma":[0.163906,0.001203951,0.001910575,0.004827309,0.002609106,0.005934078,0.006693298,0.002282007,0.001400537],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001218675,"about_ca_system_score_gemma":0.001475691,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001080274,"about_ca_topic_score_gemma":0.001014046,"domain_scores_codex":[0.9607112,0.03003109,0.001047667,0.003234788,0.004274915,0.000700353],"domain_scores_gemma":[0.9011077,0.07007089,0.006437703,0.01783371,0.003853936,0.0006960354],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004603436,0.0003406374,0.02690122,0.0005330204,0.0007980017,0.0004155098,0.00115268,0.07342136,0.001082189,0.6476023,0.002955559,0.2443373],"study_design_scores_gemma":[0.000115413,0.0004400135,0.005310322,0.000207641,0.0002364758,0.000319804,0.0002668029,0.3497747,0.001647147,0.6346092,0.00701081,0.00006182292],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009066677,0.0001552563,0.9888253,0.0002749847,0.00004456508,0.000169735,0.00009991595,0.0001179801,0.001245511],"genre_scores_gemma":[0.4284275,0.0005841523,0.5637121,0.0006637512,0.0003553542,0.001413772,0.0007478953,0.0001023622,0.003993106],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.04433987,"threshold_uncertainty_score":0.2344945,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3192595369094688,"score_gpt":0.2879491935998081,"score_spread":0.03131034330966076,"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."}}