{"id":"W4413165906","doi":"10.1080/10618600.2025.2541012","title":"Boosting Prediction with Data Missing Not at Random","year":2025,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Boosting (machine learning); Missing data; Computer science; Artificial intelligence; Random forest; Machine learning; Econometrics; Statistics; Data mining; Mathematics","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":[0.0179755,0.001138849,0.003330378,0.0007773768,0.0007319092,0.001408236,0.003150564,0.001786643,0.003102151],"category_scores_gemma":[0.03825467,0.0008148238,0.001329547,0.001057559,0.001414801,0.001861149,0.002078672,0.002922731,0.00140828],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000588503,"about_ca_system_score_gemma":0.001583174,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001198664,"about_ca_topic_score_gemma":0.001165231,"domain_scores_codex":[0.996016,0.002349231,0.0001623727,0.0005716469,0.0006219769,0.0002788181],"domain_scores_gemma":[0.9818981,0.0127643,0.0008488511,0.002605749,0.001512473,0.0003705734],"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":[0.0006683267,0.0001870145,0.007671131,0.0004957115,0.0002692367,0.0005305674,0.0002850584,0.6248094,0.002739654,0.1368865,0.009799494,0.2156579],"study_design_scores_gemma":[0.00002027945,0.00003576871,0.0002950641,0.00002318511,0.00002074099,0.0000534172,0.000007931713,0.9695928,0.0005276311,0.02820636,0.001206282,0.00001052097],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006450547,0.0002399027,0.9922126,0.0001819442,0.0000723519,0.00003758113,0.00005874074,0.0002734778,0.0004727797],"genre_scores_gemma":[0.5189665,0.0007183868,0.4742151,0.0006424121,0.0004424021,0.0004019928,0.0008299971,0.000240699,0.003542489],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0179755,"threshold_uncertainty_score":0.09506464,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02070957838485018,"score_gpt":0.2705212398444851,"score_spread":0.2498116614596349,"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."}}