{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003220128,0.0001814747,0.0006248424,0.0001212091,0.00007645586,0.00006747012,0.0007827861,0.00007742992,0.00004054435],"category_scores_gemma":[0.040359,0.0001085756,0.00002347984,0.0003829867,0.0004356799,0.0001673081,0.0002027557,0.0004115526,3.643224e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002383812,"about_ca_system_score_gemma":0.0002010105,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001933069,"about_ca_topic_score_gemma":0.000583363,"domain_scores_codex":[0.9968981,0.001124431,0.001048217,0.0002138946,0.0004690636,0.0002463357],"domain_scores_gemma":[0.9659048,0.03259286,0.0005611651,0.0004982947,0.0003690471,0.00007383765],"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":[0.001099157,0.0003247985,0.2685136,0.0004860077,0.0001036201,0.0001749711,0.001822578,0.00001438811,0.00004971974,0.6479186,0.01675352,0.06273901],"study_design_scores_gemma":[0.001366587,0.0002397599,0.3762601,0.0008234111,0.00007882334,0.00002131212,0.0002529564,0.003959204,0.00002554859,0.6168399,0.00003869965,0.00009368757],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02214896,0.0002922351,0.9748103,0.0001081528,0.0001914854,0.0002111426,0.002051087,0.000003516975,0.0001831107],"genre_scores_gemma":[0.6551129,0.0002503118,0.3445415,0.00002636419,0.00001952336,0.000001849838,0.00002579424,0.000006964516,0.00001478567],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6329639,"threshold_uncertainty_score":0.9677244,"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."}}