{"id":"W4408642178","doi":"10.1111/sjos.12777","title":"Statistical inference in the presence of imputed survey data through regression trees and random forests","year":2025,"lang":"en","type":"article","venue":"Scandinavian Journal of Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Statistics; Random forest; Statistical inference; Inference; Regression; Econometrics; Regression analysis; Artificial intelligence; Computer science","routes":{"ca_aff":true,"ca_fund":true,"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":[0.04856898,0.0009671458,0.002222876,0.002667034,0.0009211106,0.001959204,0.003375252,0.001857483,0.001252754],"category_scores_gemma":[0.1480541,0.0009613998,0.00177999,0.003631512,0.002583303,0.002752159,0.002029349,0.002734701,0.0002995732],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009642665,"about_ca_system_score_gemma":0.001492742,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005400235,"about_ca_topic_score_gemma":0.00349894,"domain_scores_codex":[0.9696389,0.02572428,0.0007699654,0.00188196,0.001470588,0.0005144178],"domain_scores_gemma":[0.7860229,0.1953061,0.007735009,0.006303141,0.004040399,0.0005923142],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002696036,0.0001139569,0.01621592,0.0003263023,0.0006012367,0.0004856398,0.0003257855,0.7193687,0.0006507732,0.174926,0.001951585,0.08476452],"study_design_scores_gemma":[0.00002712886,0.00002835388,0.0008794803,0.00006283927,0.0000410705,0.00006977272,0.00002315686,0.8876722,0.0002447358,0.1105015,0.0004346542,0.00001503315],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01441363,0.000463863,0.9844395,0.0002265872,0.00003137892,0.00002561753,0.00006108694,0.0001084583,0.0002297662],"genre_scores_gemma":[0.4813121,0.0009522526,0.5156394,0.0002657669,0.000219885,0.0002692908,0.0004506741,0.000120014,0.0007705824],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.04856898,"threshold_uncertainty_score":0.2568604,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1682633546537468,"score_gpt":0.4474455253192067,"score_spread":0.2791821706654599,"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."}}