{"id":"W2080645484","doi":"10.1002/cjs.5550360207","title":"Robust methods for generalized linear models with nonignorable missing covariates","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Outlier; Missing data; Generalized linear model; Statistics; Mathematics; Expectation–maximization algorithm; Maximum likelihood; Generalized linear mixed model; Linear model; Econometrics; Computer science; Algorithm","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"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":[0.02190115,0.002225275,0.002747548,0.002782155,0.0006816228,0.001799056,0.004600624,0.00243963,0.004638076],"category_scores_gemma":[0.07126231,0.00140568,0.003225314,0.003332481,0.002256308,0.001852543,0.003360944,0.004144122,0.00110322],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001515769,"about_ca_system_score_gemma":0.002411335,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005558434,"about_ca_topic_score_gemma":0.003881369,"domain_scores_codex":[0.9816041,0.0149565,0.0005305058,0.001228726,0.001407567,0.0002725672],"domain_scores_gemma":[0.9456092,0.0470877,0.00294485,0.002180066,0.001916086,0.0002621339],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001444809,0.00009204671,0.0009459135,0.0006797388,0.0009541097,0.0003272602,0.000252831,0.4546148,0.0008927452,0.4080822,0.004297188,0.1287167],"study_design_scores_gemma":[0.00005594944,0.00006229123,0.0003405265,0.00008890801,0.00007846927,0.00009589092,0.00003483574,0.7804062,0.0004340312,0.2136716,0.004686358,0.00004494082],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004853612,0.0003397339,0.9987267,0.0001134173,0.00002851489,0.00002169679,0.00003570161,0.00009965924,0.0001492598],"genre_scores_gemma":[0.058094,0.001431379,0.9367973,0.0001743984,0.0002801703,0.0006512929,0.0004110523,0.0002587771,0.001901745],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02190115,"threshold_uncertainty_score":0.1158257,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2633300936493123,"score_gpt":0.4128931837725661,"score_spread":0.1495630901232539,"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."}}