{"id":"W2798242991","doi":"10.1007/s00477-018-1539-8","title":"Statistics for sample splitting for the calibration and validation of hydrological models","year":2018,"lang":"en","type":"article","venue":"Stochastic Environmental Research and Risk Assessment","topic":"Hydrology and Watershed Management Studies","field":"Environmental Science","cited_by":39,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"Guangzhou Municipal Science and Technology Project; National Natural Science Foundation of China","keywords":"Goodness of fit; Calibration; Reliability (semiconductor); Statistics; Sample size determination; Sample (material); Statistical hypothesis testing; Computer science; Range (aeronautics); Population; Statistical model; Data mining; Mathematics","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":[0.03768805,0.001319375,0.002008868,0.003104694,0.001906997,0.001857443,0.003051501,0.002410475,0.0085153],"category_scores_gemma":[0.2298546,0.001429033,0.001955403,0.002915207,0.002252938,0.004420036,0.002514345,0.005165812,0.002509515],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001008606,"about_ca_system_score_gemma":0.003412101,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001890048,"about_ca_topic_score_gemma":0.002740374,"domain_scores_codex":[0.9775239,0.01460231,0.002039299,0.001712551,0.003690932,0.0004309162],"domain_scores_gemma":[0.721289,0.2259059,0.005983437,0.03421856,0.01141974,0.00118339],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00248518,0.0007714099,0.02249762,0.0008547879,0.0007555598,0.0007034137,0.0009371653,0.1836906,0.01481592,0.1440476,0.03327453,0.5951662],"study_design_scores_gemma":[0.0003222108,0.0004804563,0.006743241,0.0001551612,0.00014931,0.0003532742,0.000150395,0.8622813,0.01570495,0.1057564,0.007796304,0.0001069608],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01355568,0.0001776064,0.9822108,0.0002012024,0.00008737412,0.0001868265,0.0008072494,0.002189803,0.0005834],"genre_scores_gemma":[0.1376104,0.0001987835,0.8508304,0.0002878953,0.000227657,0.001681002,0.006472763,0.001692119,0.0009990761],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03768805,"threshold_uncertainty_score":0.1993159,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0499276736545958,"score_gpt":0.3455323242670152,"score_spread":0.2956046506124194,"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."}}