{"id":"W4388542568","doi":"10.2139/ssrn.4610561","title":"On Using Harmonized Data in Statistical Analysis: A Note of Caution","year":2023,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Statistical analysis; Econometrics; Statistics; Computer science; 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":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5192938,0.00260562,0.0118283,0.006819413,0.007255897,0.01581732,0.0198391,0.02231012,0.003157572],"category_scores_gemma":[0.6851446,0.002774243,0.005998209,0.008682275,0.04959582,0.01640565,0.009035035,0.0807151,0.005049197],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005083831,"about_ca_system_score_gemma":0.01317089,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009921484,"about_ca_topic_score_gemma":0.02272337,"domain_scores_codex":[0.4481831,0.3830027,0.05605157,0.02577158,0.08467489,0.002316124],"domain_scores_gemma":[0.1762251,0.668631,0.01548942,0.05825604,0.07745831,0.003940235],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001253729,0.000257119,0.008502199,0.007480226,0.003387403,0.003874075,0.02755287,0.00200159,0.002997738,0.162058,0.6483551,0.1322799],"study_design_scores_gemma":[0.001083709,0.000554613,0.008862754,0.03114254,0.00155451,0.004906147,0.01063274,0.01173248,0.004767779,0.4451221,0.4783515,0.001289047],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"methods","genre_scores_codex":[0.004609345,0.03022013,0.3594616,0.5285034,0.0652765,0.001417175,0.0009372038,0.001230878,0.008343708],"genre_scores_gemma":[0.03598647,0.007513687,0.3854183,0.5311874,0.03067672,0.003059947,0.0002105415,0.001326232,0.004620803],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4807062,"threshold_uncertainty_score":0.5927963,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1833010166755009,"score_gpt":0.486145505220095,"score_spread":0.3028444885445941,"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."}}