{"id":"W3126130238","doi":"","title":"Too Good to Be True? Fallacies in Evaluating Risk Factor Models","year":2017,"lang":"en","type":"preprint","venue":"RePEc: Research Papers in Economics","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Spurious relationship; Econometrics; Capital asset pricing model; Identification (biology); Uncorrelated; Inference; Factor analysis; Economics; Zhàng; Statistical hypothesis testing; Mathematics; Statistics; Computer science","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":[0.1291246,0.001906676,0.003499507,0.004825085,0.002055118,0.01035321,0.00360906,0.005023268,0.002244715],"category_scores_gemma":[0.4821212,0.00188319,0.00178459,0.002923472,0.009083681,0.01322139,0.005459285,0.00802727,0.0008861493],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002539263,"about_ca_system_score_gemma":0.002907714,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002478946,"about_ca_topic_score_gemma":0.002258728,"domain_scores_codex":[0.9185851,0.05826409,0.004895514,0.005968639,0.01129411,0.0009925785],"domain_scores_gemma":[0.6171349,0.3397385,0.01068324,0.02190772,0.008682325,0.001853217],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0006778202,0.0002611388,0.04036402,0.0008536139,0.001206073,0.0007850713,0.003195559,0.1510834,0.0009850363,0.534934,0.01124343,0.2544108],"study_design_scores_gemma":[0.00005426925,0.00009121656,0.001557679,0.0002811537,0.00006780552,0.0002431892,0.0003990147,0.2082563,0.0008611993,0.7861831,0.001944515,0.00006051039],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06728275,0.004019284,0.9085577,0.01131373,0.0003860219,0.0001511972,0.0002995489,0.0008421745,0.007147538],"genre_scores_gemma":[0.6373268,0.001431207,0.3562485,0.002315728,0.0005830131,0.000282894,0.0004136079,0.0004022876,0.0009959906],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8708754,"threshold_uncertainty_score":0.6828843,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4142245880651185,"score_gpt":0.5169482542233198,"score_spread":0.1027236661582013,"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."}}