{"id":"W4286892113","doi":"10.48550/arxiv.2110.14465","title":"Unbiased Statistical Estimation and Valid Confidence Intervals Under Differential Privacy","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Confidence interval; Statistics; Mathematics; Robust confidence intervals; Confidence distribution; CDF-based nonparametric confidence interval; Best linear unbiased prediction; Coverage probability; Unbiased Estimation; Covariance; Confidence and prediction bands; Estimation theory; Differential privacy; Computer science; Artificial intelligence","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":[],"consensus_categories":[],"category_scores_codex":[0.02775735,0.001673352,0.002580693,0.003887227,0.00139204,0.004982654,0.003884908,0.003094228,0.00246964],"category_scores_gemma":[0.2415986,0.001438265,0.001988996,0.003595792,0.005448634,0.008587215,0.007920492,0.006330454,0.001225564],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001741524,"about_ca_system_score_gemma":0.002186562,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005931866,"about_ca_topic_score_gemma":0.0003227819,"domain_scores_codex":[0.9656568,0.0172379,0.001803081,0.004419153,0.009395531,0.001487633],"domain_scores_gemma":[0.7923301,0.1494337,0.01078745,0.03585073,0.01022824,0.001369717],"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":[0.0004871582,0.0001036108,0.003537533,0.0002853411,0.0002195032,0.0005378668,0.0006903146,0.1651399,0.006290228,0.6905573,0.00239552,0.1297557],"study_design_scores_gemma":[0.00005568069,0.000106519,0.0004514794,0.0001113589,0.00004782662,0.0004156915,0.00005750661,0.4458183,0.0120251,0.537778,0.003065162,0.00006739092],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002441127,0.0001007313,0.9964399,0.0001116515,0.00001383712,0.00002045857,0.0000499944,0.0001911019,0.0006311828],"genre_scores_gemma":[0.368685,0.0006098482,0.626872,0.0005499556,0.0002497015,0.0005308736,0.0005384012,0.0004502918,0.001513954],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02775735,"threshold_uncertainty_score":0.1467966,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.113793641154091,"score_gpt":0.2491359555914709,"score_spread":0.13534231443738,"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."}}