{"id":"W4415113455","doi":"10.1214/25-ejs2446","title":"Online inference in high-dimensional regression with streaming clustered data","year":2025,"lang":"en","type":"article","venue":"Electronic Journal of Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Alberta Machine Intelligence Institute; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; Canadian Institute for Advanced Research","keywords":"Estimator; Consistency (knowledge bases); Inference; Raw data; Statistical inference; Streaming data; Asymptotic distribution; Regression analysis; Volume (thermodynamics)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008917916,0.0001736209,0.0004484211,0.0001913402,0.00005286657,0.00002947998,0.0004679084,0.00006689976,0.00006382873],"category_scores_gemma":[0.005236432,0.0001185653,0.00001699385,0.0002966448,0.00008430999,0.0001187212,0.0001537634,0.0007699846,6.748527e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001781215,"about_ca_system_score_gemma":0.001093255,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004158133,"about_ca_topic_score_gemma":0.0004774726,"domain_scores_codex":[0.9980757,0.0001885096,0.0007215287,0.0002053631,0.0003860683,0.0004228741],"domain_scores_gemma":[0.9948215,0.003987728,0.0004422316,0.0003831985,0.0002963053,0.00006897454],"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":[0.0003665774,0.0005331545,0.001791287,0.0001311375,0.0001186662,0.0001309043,0.00007138338,0.0001483061,0.0001880495,0.8916163,0.002137111,0.1027672],"study_design_scores_gemma":[0.001880826,0.0007317094,0.006632154,0.001242715,0.0001358474,0.00004794168,0.0001208075,0.03258429,0.0001265831,0.9561242,0.000176863,0.000196041],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07458099,0.0002735572,0.9243041,0.0002627507,0.0001172409,0.0000958907,0.0002928952,0.000007906065,0.00006464696],"genre_scores_gemma":[0.4848383,0.000120749,0.5148109,0.00006232347,0.00003707975,7.455453e-7,0.00002734097,0.00001086589,0.00009175918],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4102573,"threshold_uncertainty_score":0.6268877,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06587785787111924,"score_gpt":0.3924980359292162,"score_spread":0.326620178058097,"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."}}