{"id":"W4377690683","doi":"10.1111/biom.13881","title":"Instability of Inverse Probability Weighting Methods and a Remedy for Nonignorable Missing Data","year":2023,"lang":"en","type":"article","venue":"Biometrics","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"National Key Research and Development Program of China; Higher Education Discipline Innovation Project; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Inverse probability weighting; Missing data; Weighting; Instability; Inverse probability; Statistics; Inverse; Mathematics; Econometrics; Computer science; Medicine; Bayesian probability; Posterior probability; Physics; Propensity score matching; Radiology; Geometry","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":[0.008123866,0.0001226364,0.0003804777,0.0004796417,0.0001071718,0.00004013239,0.0003095973,0.0001010194,0.00001780506],"category_scores_gemma":[0.0783097,0.0001038091,0.00003861883,0.003756906,0.0001781925,0.0001217328,0.0003796697,0.00009075799,0.000001186815],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003752716,"about_ca_system_score_gemma":0.00009459226,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000336124,"about_ca_topic_score_gemma":0.00000663336,"domain_scores_codex":[0.9982669,0.0003121365,0.0005075749,0.0004372426,0.0002088262,0.0002673515],"domain_scores_gemma":[0.9859424,0.0127179,0.0002050557,0.0008068032,0.0002188351,0.0001089873],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003929361,0.0001899981,0.005274574,0.002838822,0.00003944416,0.000001877389,0.0002718871,1.268769e-7,0.007691544,0.1090481,0.001449721,0.8731546],"study_design_scores_gemma":[0.0003130057,0.00008914134,0.00235406,0.00005555499,0.00005898561,0.000001383591,0.0001078449,0.03188251,0.00363828,0.9589539,0.002393518,0.0001518312],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02652578,0.00005928225,0.9718853,0.0001334751,0.0001293054,0.0004728822,0.0003255358,0.00007888123,0.000389525],"genre_scores_gemma":[0.005804318,0.00002041401,0.9940589,0.00001298991,0.0000275472,0.00001567042,0.00002248302,0.00001525026,0.00002244896],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8730027,"threshold_uncertainty_score":0.9294541,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4313019177408205,"score_gpt":0.5069443664946836,"score_spread":0.07564244875386306,"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."}}