{"id":"W4388558959","doi":"10.1002/9781119712206.ch20","title":"On Using Harmonized Data in Statistical Analysis: Notes of Caution","year":2023,"lang":"en","type":"other","venue":"","topic":"Forecasting Techniques and Applications","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Weighting; Set (abstract data type); Computer science; Data science; Data set; Data mining; Missing data; Operations research; Machine learning; Artificial intelligence; Engineering","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":[0.6636444,0.002750671,0.00786378,0.00824054,0.007303044,0.02246647,0.01713717,0.0126088,0.003408634],"category_scores_gemma":[0.7929565,0.003142775,0.006562194,0.01426926,0.05869749,0.02895138,0.01470147,0.06857856,0.004420065],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.008554188,"about_ca_system_score_gemma":0.01669502,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01045583,"about_ca_topic_score_gemma":0.0136646,"domain_scores_codex":[0.2303102,0.6245899,0.04444272,0.0175829,0.08119986,0.001874477],"domain_scores_gemma":[0.09956013,0.7692159,0.0117322,0.05771627,0.05971048,0.002065063],"domain_codex":"methods","domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004625722,0.0001378004,0.004611159,0.004876057,0.001732194,0.0007936091,0.02482675,0.003466112,0.0005771058,0.3421782,0.4927178,0.1236205],"study_design_scores_gemma":[0.0002832017,0.0001968979,0.002759691,0.01649367,0.0003289111,0.0008919486,0.007980512,0.007862963,0.00126563,0.5184729,0.4429299,0.0005338318],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.002804191,0.02863397,0.3440589,0.5805759,0.03111273,0.001432291,0.0008614742,0.001166936,0.009353604],"genre_scores_gemma":[0.0434717,0.01507357,0.5108578,0.3979376,0.02065306,0.005000699,0.0003682393,0.001954719,0.004682573],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.6636444,"threshold_uncertainty_score":0.4147864,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4979854027115637,"score_gpt":0.5258167326672998,"score_spread":0.02783132995573612,"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."}}