{"id":"W4391509064","doi":"10.1016/j.eeh.2024.101579","title":"Linked samples and measurement error in historical US census data","year":2024,"lang":"en","type":"article","venue":"Explorations in Economic History","topic":"Health disparities and outcomes","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Canada Excellence Research Chairs, Government of Canada","keywords":"Census; False positive paradox; Statistics; Observational error; Data quality; Econometrics; Demography; Geography; Mathematics; Economics; Sociology; Population; Operations management","routes":{"ca_aff":true,"ca_fund":true,"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":[0.05444358,0.0005075911,0.0005800666,0.002816371,0.00156853,0.002475656,0.001437633,0.001021465,0.002171381],"category_scores_gemma":[0.3377084,0.000613286,0.0006718839,0.006802675,0.001886917,0.00226359,0.002227291,0.001841643,0.000529263],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001847269,"about_ca_system_score_gemma":0.001617253,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0237349,"about_ca_topic_score_gemma":0.01734843,"domain_scores_codex":[0.9258904,0.05141057,0.004608021,0.006939338,0.00978221,0.00136941],"domain_scores_gemma":[0.7240719,0.1820294,0.04636001,0.0364647,0.01029102,0.000782844],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002327286,0.0001285947,0.8861641,0.0002436601,0.0009855718,0.0002001741,0.004747419,0.01319401,0.0002760215,0.03598525,0.007170296,0.05067218],"study_design_scores_gemma":[0.0001578709,0.0002802972,0.732074,0.001231252,0.000833145,0.000966779,0.005459446,0.09265167,0.006439317,0.1085752,0.05112631,0.0002047146],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7440273,0.002919646,0.2250832,0.005387857,0.0007539355,0.000458696,0.007362522,0.0005721034,0.01343486],"genre_scores_gemma":[0.9728372,0.0002974994,0.02147609,0.0006163525,0.0001359207,0.0002634417,0.002981664,0.00007482611,0.001316913],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05444358,"threshold_uncertainty_score":0.2879286,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3653689705395877,"score_gpt":0.3678990129569599,"score_spread":0.002530042417372147,"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."}}