{"id":"W4391247896","doi":"10.1016/j.csda.2024.107919","title":"A unified framework of analyzing missing data and variable selection using regularized likelihood","year":2024,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Missing data; Feature selection; Mathematics; Model selection; Maximum likelihood; Variable (mathematics); Statistics; Computer science; Artificial intelligence","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":[],"consensus_categories":[],"category_scores_codex":[0.0015732,0.0001835616,0.0005253702,0.000397526,0.0001759305,0.0002900042,0.0004672642,0.00009159632,0.0002441369],"category_scores_gemma":[0.00531493,0.0001789801,0.00003620584,0.002167179,0.0001165357,0.0002579204,0.0005475635,0.000234193,0.000001792353],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004368434,"about_ca_system_score_gemma":0.0002654386,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003451879,"about_ca_topic_score_gemma":0.00002994446,"domain_scores_codex":[0.9976786,0.0002662285,0.0006844161,0.0007090754,0.0004388225,0.0002228667],"domain_scores_gemma":[0.9919036,0.00663883,0.000224612,0.0008301607,0.000289499,0.0001132706],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002157118,0.00007783976,0.001432655,0.0004643334,0.002504125,0.00001260059,0.0001276034,0.004285566,0.0002254468,0.9563805,0.001121332,0.03334636],"study_design_scores_gemma":[0.0000534592,0.000009609716,0.000590944,0.00009293859,0.002394834,0.000003761428,0.000009935071,0.5192732,0.000003306043,0.4773968,0.00007363892,0.00009752129],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001113071,0.0003029855,0.9885558,0.00005293309,0.00007254011,0.00009107043,0.009726159,0.0000496446,0.00003582808],"genre_scores_gemma":[0.0376845,0.00002620423,0.9581692,0.00002073417,0.00006649149,0.000001197241,0.003996908,0.00002261819,0.00001216],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5149876,"threshold_uncertainty_score":0.7298595,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1362875778691583,"score_gpt":0.4247681745130699,"score_spread":0.2884805966439115,"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."}}