{"id":"W2625701074","doi":"","title":"Fast Robust Model Selection in Large Datasets","year":2010,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"HEC Montréal","funders":"","keywords":"Outlier; Estimator; Selection (genetic algorithm); Covariate; Computer science; Robust regression; Model selection; Context (archaeology); Robustness (evolution); Linear regression; Robust statistics; Feature selection; Linear model; Regression; Statistics; Machine learning; Mathematics; Artificial intelligence","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":[],"consensus_categories":[],"category_scores_codex":[0.03155526,0.002490334,0.003729384,0.003007761,0.001292392,0.002296993,0.00362372,0.002474568,0.00283458],"category_scores_gemma":[0.08169519,0.001607775,0.003326873,0.003682761,0.001350269,0.002907489,0.003618669,0.004019251,0.001626088],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001000114,"about_ca_system_score_gemma":0.00310559,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004609804,"about_ca_topic_score_gemma":0.006217747,"domain_scores_codex":[0.9834068,0.01305273,0.0006107456,0.001325581,0.001299395,0.0003046985],"domain_scores_gemma":[0.9332559,0.05618622,0.002283822,0.005866939,0.002010305,0.000396764],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004658336,0.0001585104,0.003704544,0.0006857846,0.001064112,0.0006986948,0.0002167698,0.7208396,0.002364016,0.04389925,0.008017341,0.2178857],"study_design_scores_gemma":[0.0001046267,0.00007774666,0.0007421327,0.0000399056,0.00008201829,0.0001368535,0.00004397871,0.9258109,0.001125379,0.0694993,0.002296644,0.00004059747],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003029852,0.0002976409,0.9952729,0.0002339785,0.00002373318,0.00007674738,0.0001823683,0.0007391343,0.0001436382],"genre_scores_gemma":[0.07839774,0.000543377,0.916986,0.0003164858,0.0001595256,0.0009254779,0.00151196,0.0004037261,0.0007556928],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03155526,"threshold_uncertainty_score":0.1668821,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04707642951867836,"score_gpt":0.3820002722049438,"score_spread":0.3349238426862655,"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."}}