{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1721087,0.001767536,0.004688339,0.003922544,0.001956616,0.003652601,0.004973338,0.004312179,0.005723274],"category_scores_gemma":[0.5534517,0.001224906,0.003495223,0.00510783,0.006044447,0.006468345,0.005470437,0.005797874,0.001164767],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001380777,"about_ca_system_score_gemma":0.004574898,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003559049,"about_ca_topic_score_gemma":0.00277625,"domain_scores_codex":[0.8492379,0.1325015,0.004119725,0.006863388,0.006146302,0.0011312],"domain_scores_gemma":[0.2611745,0.6921115,0.01070797,0.02770585,0.00661734,0.001682759],"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":[0.004728133,0.0006316396,0.1523988,0.002080911,0.005860642,0.002776474,0.003975013,0.2735187,0.003769219,0.1142326,0.0162094,0.4198184],"study_design_scores_gemma":[0.0008001564,0.002100606,0.02609154,0.0004232466,0.0007025081,0.001107021,0.0008852339,0.7485811,0.003880908,0.2069429,0.008093701,0.0003911663],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05727018,0.001241735,0.935829,0.00179743,0.0002126844,0.0004522939,0.0004211252,0.001161606,0.001613927],"genre_scores_gemma":[0.5568715,0.0005046009,0.4370095,0.001394177,0.0004515059,0.001341661,0.0008749248,0.0006464311,0.0009056625],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1721087,"threshold_uncertainty_score":0.9102086,"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."}}