{"id":"W4387972453","doi":"10.1080/02664763.2023.2272223","title":"Improving the Hosmer-Lemeshow goodness-of-fit test in large models with replicated Bernoulli trials","year":2023,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Economic and Environmental Valuation","field":"Economics, Econometrics and Finance","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Goodness of fit; Covariate; Logistic regression; Statistics; Type I and type II errors; Bernoulli trial; Bernoulli's principle; Mathematics; Test (biology); Sample size determination; Computer science; Econometrics; Biology","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":[0.003261321,0.0001139109,0.0005687936,0.0001799789,0.00005687933,0.00003100832,0.0001987136,0.000060231,0.00009094545],"category_scores_gemma":[0.000227556,0.00008990084,0.00005882582,0.0002286997,0.00005174995,0.0001159497,0.00004349574,0.0001964331,0.00005339211],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000107397,"about_ca_system_score_gemma":0.00003580225,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003635289,"about_ca_topic_score_gemma":0.00002244375,"domain_scores_codex":[0.998192,0.00001698533,0.001355993,0.0001667817,0.00006882493,0.0001994502],"domain_scores_gemma":[0.9974105,0.0005165433,0.001791622,0.0002115994,0.00002357474,0.00004612791],"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":[0.0004167128,0.0006091524,0.1630352,0.0001599482,0.0003506614,0.00002873459,0.003172703,0.09276188,0.001082609,0.7207752,0.005979276,0.0116279],"study_design_scores_gemma":[0.008581895,0.0007842275,0.3180537,0.00008957295,0.0001593108,0.00002287294,0.003363885,0.2958944,0.00111924,0.3683899,0.002803064,0.0007379689],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.796124,0.0002820244,0.1970794,0.0004187593,0.0002316777,0.0005682041,0.001661507,0.00001532829,0.003619008],"genre_scores_gemma":[0.9921069,0.0003222577,0.007242105,0.00006802294,0.00006406275,0.00001373082,0.0000275474,0.0000236302,0.0001318047],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3523853,"threshold_uncertainty_score":0.366605,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1822081850794053,"score_gpt":0.2738585338142405,"score_spread":0.09165034873483516,"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."}}