{"id":"W4407204977","doi":"10.1016/j.ajo.2025.01.022","title":"Which Test Is Best: Evaluation of Traditional and Contemporary Statistical Tests for Analysis of Spherical Equivalent Prediction Error","year":2025,"lang":"en","type":"article","venue":"American Journal of Ophthalmology","topic":"Ophthalmology and Visual Impairment Studies","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Electrik Box (Canada); McGill University","funders":"Ministero della Salute; Rome Foundation","keywords":"Test (biology); Statistics; Statistical analysis; Mathematics; Error analysis; Computer science; Applied mathematics; Biology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.09608793,0.001066491,0.003122746,0.004335588,0.0009972897,0.002250973,0.003994573,0.001821647,0.003773041],"category_scores_gemma":[0.2807598,0.0003561817,0.002692038,0.004098415,0.003127192,0.005501575,0.001957562,0.002181518,0.000358334],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001403762,"about_ca_system_score_gemma":0.001626506,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001469737,"about_ca_topic_score_gemma":0.0018548,"domain_scores_codex":[0.9318308,0.04886295,0.005195099,0.004543073,0.008962601,0.0006055172],"domain_scores_gemma":[0.446339,0.5236341,0.01131155,0.006809899,0.009875685,0.002029794],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.05367304,0.001953227,0.427133,0.005126536,0.01796574,0.0007738532,0.002640042,0.01558823,0.003730981,0.01661949,0.01126522,0.4435307],"study_design_scores_gemma":[0.00668188,0.05688121,0.4027985,0.001474913,0.01190983,0.002905955,0.006884994,0.4596631,0.009345353,0.03248082,0.008227286,0.0007462031],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7585045,0.01056418,0.219657,0.002411007,0.001095433,0.001027109,0.002153587,0.0009525982,0.003634626],"genre_scores_gemma":[0.9270909,0.0008776217,0.06994495,0.0002208091,0.0002769989,0.0004885052,0.0004756182,0.00024021,0.0003844099],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9039121,"threshold_uncertainty_score":0.5081676,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1580162128185588,"score_gpt":0.4503470860078424,"score_spread":0.2923308731892836,"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."}}