{"id":"W3021200516","doi":"","title":"PROPENSITY WEIGHTING FOR SURVEY NONRESPONSE THROUGH MACHINE LEARNING","year":2018,"lang":"fr","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Nonparametric statistics; Weighting; Estimator; Boosting (machine learning); Statistics; Parametric statistics; Propensity score matching; Computer science; Inverse probability weighting; Non-response bias; Econometrics; Context (archaeology); Parametric model; Machine learning; Mathematics; Geography","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","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2913106,0.0006387158,0.0009712827,0.0001691365,0.00335805,0.0004087653,0.002027767,0.001031347,0.0009100909],"category_scores_gemma":[0.1792626,0.0006904902,0.0004801948,0.0009838566,0.00234604,0.0003631278,0.001579521,0.001510868,0.0002632052],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002976859,"about_ca_system_score_gemma":0.001209677,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.03980726,"about_ca_topic_score_gemma":0.07725554,"domain_scores_codex":[0.6572614,0.3387277,0.000948105,0.001468727,0.0006171559,0.0009769356],"domain_scores_gemma":[0.8711685,0.1198611,0.001217691,0.001759669,0.005675817,0.0003172283],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.01605415,0.003636939,0.3468137,0.0007197153,0.001255825,0.00004288837,0.2885889,0.0001916517,0.005914468,0.2429118,0.007322319,0.08654761],"study_design_scores_gemma":[0.002123863,0.000008359545,0.3966221,0.002569057,0.0002621153,0.0000263865,0.0008747027,0.0119424,0.03691169,0.01301221,0.5336288,0.002018321],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6597452,0.002420372,0.2889781,0.01620386,0.001826614,0.001521287,0.0003665997,0.0003122252,0.02862569],"genre_scores_gemma":[0.5845247,0.002195115,0.2543372,0.0003566817,0.0002788892,0.0002209276,0.001583787,0.0001511153,0.1563517],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5263065,"threshold_uncertainty_score":0.9995546,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1782488208618073,"score_gpt":0.3677460359588443,"score_spread":0.1894972150970369,"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."}}