{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Qiu H"],"funding":["NIA NIH HHS","NCI NIH HHS","DMS","NIH","NIGMS NIH HHS"],"pagination":["1680-1705"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC10837005"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["85(5)"],"pubmed_abstract":["Predicting sets of outcomes-instead of unique outcomes-is a promising solution to uncertainty quantification in statistical learning. Despite a rich literature on constructing prediction sets with statistical guarantees, adapting to unknown covariate shift-a prevalent issue in practice-poses a serious unsolved challenge. In this article, we show that prediction sets with finite-sample coverage guarantee are uninformative and propose a novel flexible distribution-free method, PredSet-1Step, to efficiently construct prediction sets with an asymptotic coverage guarantee under unknown covariate shift. We formally show that our method is <i>asymptotically probably approximately correct</i>, having well-calibrated coverage error with high confidence for large samples. We illustrate that it achie"],"journal":["Journal of the Royal Statistical Society. Series B, Statistical methodology"],"pubmed_title":["Prediction sets adaptive to unknown covariate shift."],"pmcid":["PMC10837005"],"funding_grant_id":["2046874","R01 AG065276","R01 GM139926","grants R01AI27271, R01CA222147, R01AG065276, R01GM139926","R01 CA222147"],"pubmed_authors":["Dobriban E","Qiu H","Tchetgen Tchetgen E"],"additional_accession":[]},"is_claimable":false,"name":"Prediction sets adaptive to unknown covariate shift.","description":"Predicting sets of outcomes-instead of unique outcomes-is a promising solution to uncertainty quantification in statistical learning. Despite a rich literature on constructing prediction sets with statistical guarantees, adapting to unknown covariate shift-a prevalent issue in practice-poses a serious unsolved challenge. In this article, we show that prediction sets with finite-sample coverage guarantee are uninformative and propose a novel flexible distribution-free method, PredSet-1Step, to efficiently construct prediction sets with an asymptotic coverage guarantee under unknown covariate shift. We formally show that our method is <i>asymptotically probably approximately correct</i>, having well-calibrated coverage error with high confidence for large samples. We illustrate that it achie","dates":{"release":"2023-01-01T00:00:00Z","publication":"2023 Nov","modification":"2025-04-25T19:13:51.575Z","creation":"2025-04-06T07:54:01.561Z"},"accession":"S-EPMC10837005","cross_references":{"pubmed":["38312527"],"doi":["10.1093/jrsssb/qkad069"]}}