{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003049442,0.0004141391,0.0006042121,0.0001153486,0.000260532,0.0001104231,0.0004443399,0.0004941676,0.00004517127],"category_scores_gemma":[0.00207812,0.0004608734,0.0001460323,0.0003262491,0.0004182245,0.000256859,0.0006410042,0.0005242296,0.00001423017],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002634479,"about_ca_system_score_gemma":0.0001751274,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001925053,"about_ca_topic_score_gemma":0.0004505162,"domain_scores_codex":[0.9971894,0.0007340753,0.0004541649,0.001156305,0.0001249657,0.0003410953],"domain_scores_gemma":[0.9959133,0.001814108,0.0004986053,0.001061163,0.0005964824,0.0001163418],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0006129711,0.0008679056,0.8028337,0.003983095,0.0005372959,0.00003054272,0.003547358,0.01527798,0.00008306365,0.1686507,0.002485728,0.001089686],"study_design_scores_gemma":[0.0003101824,0.00007559057,0.04687729,0.0001742835,0.00008473111,0.000001464759,0.00005563618,0.02784949,0.0002874501,0.9238319,0.00001482355,0.0004371324],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5567784,0.000007362686,0.4416758,0.00001371374,0.0001475106,0.0005012231,0.000102122,0.000336723,0.0004371615],"genre_scores_gemma":[0.9032117,0.00003909154,0.0963769,0.00001826808,0.00004270429,0.000004985263,0.0001833364,0.00003712009,0.00008587862],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7559564,"threshold_uncertainty_score":0.9997843,"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."}}