{"id":"W4210320674","doi":"10.1002/cjs.11688","title":"Statistical data integration using multilevel models to predict employee compensation","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Survey data collection; Variable (mathematics); Econometrics; Estimation; Multilevel model; Variables; Statistics; Computer science; Wage; Hierarchical database model; Data mining; Mathematics; Engineering; Economics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001167954,0.0001665847,0.0003652694,0.0003161107,0.0003658351,0.0001052662,0.0006269793,0.0000424818,0.0008372652],"category_scores_gemma":[0.003537052,0.0001661668,0.00002551372,0.0002118332,0.00009468371,0.0002061729,0.0001097862,0.0004583334,0.000003773788],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004328844,"about_ca_system_score_gemma":0.001677388,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002254301,"about_ca_topic_score_gemma":0.003923499,"domain_scores_codex":[0.9977515,0.0003487289,0.0007947461,0.0002274847,0.0005259982,0.0003515749],"domain_scores_gemma":[0.9965471,0.001534335,0.0003264453,0.0004023331,0.0004414608,0.0007483457],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004413158,0.00003850671,0.0005779361,0.00003595004,0.0000471574,0.0003077388,0.001083228,0.00127864,0.0000770636,0.9159577,0.02978639,0.05076549],"study_design_scores_gemma":[0.0002965649,0.0002625865,0.001314934,0.00005146131,0.0001104617,0.0001820042,0.0005318503,0.2742326,0.00001049066,0.7222515,0.0005677449,0.0001878206],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003371072,0.00001729341,0.9772013,0.00008848169,0.0005688586,0.0002131249,0.01840035,0.00000813997,0.000131351],"genre_scores_gemma":[0.2267999,0.000001412592,0.7727823,0.0001504039,0.00009510456,0.000003315127,0.0001241987,0.00002730887,0.00001615426],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.272954,"threshold_uncertainty_score":0.9167467,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2992427249109633,"score_gpt":0.3907442439379452,"score_spread":0.09150151902698189,"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."}}