{"id":"W4411772179","doi":"10.5539/ijsp.v14n2p5","title":"Simpson’s Paradox: Aggregation Effects in Statistical and Machine Learning Models","year":2025,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Mathematical economics; Computer science; Statistical learning; Econometrics; Mathematics; Machine learning; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009958603,0.0001234544,0.0003092104,0.0001270121,0.0000441563,0.00005426475,0.0001027185,0.00005561372,0.00001128255],"category_scores_gemma":[0.004792339,0.0001041291,0.0000217056,0.00006020958,0.0001247185,0.0001467791,0.00007042116,0.0003294497,1.514533e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008349996,"about_ca_system_score_gemma":0.00006157051,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003047138,"about_ca_topic_score_gemma":0.00004452705,"domain_scores_codex":[0.9986073,0.0002308569,0.0005938858,0.000175709,0.0002603681,0.0001318368],"domain_scores_gemma":[0.9950921,0.004194462,0.000225618,0.00006512935,0.0003421935,0.0000805255],"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":[0.0001837225,0.0001013778,0.003136022,0.0001712491,0.00004496289,0.0000470845,0.0001829493,0.000671492,0.00002435608,0.8271334,0.00004944655,0.1682539],"study_design_scores_gemma":[0.0007812732,0.0001183709,0.003343059,0.0001525322,0.00003080804,0.00002141382,0.00001660748,0.1279087,0.00003318506,0.8673934,0.0001244445,0.00007623951],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02192482,0.0002998934,0.9768069,0.0002792638,0.0001920585,0.0001612796,0.0001420724,0.000006347071,0.0001873513],"genre_scores_gemma":[0.4422694,0.0002044676,0.5574188,0.00004455177,0.00001951532,0.000004043924,0.00000512679,0.000005509554,0.00002862338],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4203446,"threshold_uncertainty_score":0.5737224,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06134224647241327,"score_gpt":0.3888597566167712,"score_spread":0.3275175101443579,"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."}}