{"id":"W4408338912","doi":"10.3390/e27030289","title":"Practical Consequences of the Bias in the Laplace Approximation to Marginal Likelihood for Hierarchical Models","year":2025,"lang":"en","type":"article","venue":"Entropy","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"National Science Foundation","keywords":"Laplace's method; Marginal likelihood; Markov chain Monte Carlo; Posterior probability; Applied mathematics; Marginal distribution; Mathematics; Likelihood function; Laplace transform; Bayesian probability; Mathematical optimization; Computer science; Algorithm; Statistical physics; Statistics; Estimation theory; Random variable; Mathematical analysis; Physics","routes":{"ca_aff":true,"ca_fund":false,"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":[0.000942494,0.00007540962,0.0001599355,0.00004011322,0.00005703113,0.00003025437,0.000212786,0.00004566137,0.00001891858],"category_scores_gemma":[0.005584216,0.00003944859,0.0000507271,0.0002275478,0.0001021895,0.0000405326,0.0000422704,0.0001577321,0.000001583311],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000226577,"about_ca_system_score_gemma":0.0001274976,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000132335,"about_ca_topic_score_gemma":0.00001017912,"domain_scores_codex":[0.9988573,0.0003901704,0.0002581846,0.0001330687,0.0001956321,0.0001656654],"domain_scores_gemma":[0.9941666,0.005470448,0.00006869938,0.0002135019,0.00005599798,0.00002479709],"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":[0.00008078881,0.00009184632,0.0001456415,0.00006900528,0.000007718369,8.123604e-7,0.0003789633,0.00000330865,0.0004260728,0.9942113,0.002350318,0.002234208],"study_design_scores_gemma":[0.0002482968,0.00005804879,0.0004126794,0.00007902364,0.00002478755,0.000003120067,0.0002198781,0.01167712,0.001930338,0.9849881,0.0003129541,0.00004565183],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007344766,0.000007490491,0.9730245,0.01714879,0.00008440116,0.0006429538,0.00002452179,0.000008135896,0.001714375],"genre_scores_gemma":[0.3128979,0.000001723385,0.6865114,0.0004231007,0.00002118077,0.00009591608,6.70599e-7,0.000003417021,0.00004468475],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3055531,"threshold_uncertainty_score":0.6685232,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.128086404913759,"score_gpt":0.417330998368811,"score_spread":0.289244593455052,"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."}}