{"id":"W1866446821","doi":"10.1002/sta4.95","title":"The perils of quasi‐likelihood information criteria","year":2015,"lang":"en","type":"article","venue":"Stat","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Jewish General Hospital; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Selection (genetic algorithm); Correlation; Statistics; Econometrics; Model selection; Information Criteria; Mathematics; Sample (material); Matrix (chemical analysis); Computer science; Machine learning","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2074656,0.001548896,0.003785549,0.003881005,0.002250491,0.007839008,0.005559969,0.004232309,0.004642397],"category_scores_gemma":[0.5233025,0.001743961,0.002028219,0.004043194,0.01330972,0.01112015,0.006269668,0.01118288,0.001105763],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003588106,"about_ca_system_score_gemma":0.005324568,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003134822,"about_ca_topic_score_gemma":0.002002293,"domain_scores_codex":[0.7848261,0.1861789,0.005980306,0.004632721,0.01743188,0.0009501852],"domain_scores_gemma":[0.2770277,0.6727689,0.01116006,0.02436371,0.01348725,0.001192413],"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":[0.0001075725,0.00003473167,0.001264694,0.0003984758,0.0001807174,0.0001135359,0.0006277352,0.009034082,0.0001260376,0.9472234,0.002387872,0.03850103],"study_design_scores_gemma":[0.00007045246,0.00008281419,0.0005516135,0.0003024293,0.00002817842,0.00009920913,0.0001089143,0.05778819,0.0003618869,0.9350899,0.005453459,0.00006292197],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00462451,0.002577028,0.9793754,0.007506825,0.0002266022,0.0001664998,0.0001392441,0.0001535569,0.005230293],"genre_scores_gemma":[0.2900954,0.002516341,0.695106,0.005220416,0.001225237,0.001993813,0.0003982461,0.0005193495,0.002925199],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2074656,"threshold_uncertainty_score":0.9773359,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08157430578771294,"score_gpt":0.4012855105905634,"score_spread":0.3197112048028504,"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."}}