Conformal Multi‐Target Hyperrectangles
Statistical Analysis and Data Mining: The ASA Data Science Journal · 2024-10 · 17 (5)
DOI: 10.1002/sam.11710 ↗Kurz gefasst
Fachartikel in der Zeitschrift Statistical Analysis and Data Mining: The ASA Data Science Journal, online erschienen am 16.09.2024. Verfasst von Max Sampson und 1 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
We propose conformal hyperrectangular prediction regions for multi‐target regression. We propose split conformal prediction algorithms for both point and quantile regression to form hyperrectangular prediction regions, which allow for easy marginal interpretation and do not require covariance estimation. In practice, it is preferable that a prediction region is balanced, that is, having identical marginal prediction coverage, since prediction accuracy is generally equally important across components of the response vector. The proposed algorithms possess two desirable properties, namely, tight asymptotic overall nominal coverage as well as asymptotic balance, that is, identical asymptotic marginal coverage, under mild conditions. We then compare our methods to some existing methods on both simulated and real data sets. Our simulation results and real data analysis show that our methods outperform existing methods while achieving the desired nominal coverage and good balance between dimensions.
Zitieren
APA
Sampson, M., & Chan, K. (2024). Conformal Multi‐Target Hyperrectangles. Statistical Analysis and Data Mining: The ASA Data Science Journal, 17(5). https://doi.org/10.1002/sam.11710
Vancouver
Sampson M, Chan K. Conformal Multi‐Target Hyperrectangles. Statistical Analysis and Data Mining: The ASA Data Science Journal. 2024;17(5). doi:10.1002/sam.11710
BibTeX
@article{Sampson2024,
author = {Sampson, Max and Chan, Kung‐Sik},
title = {Conformal Multi‐Target Hyperrectangles},
journal = {Statistical Analysis and Data Mining: The ASA Data Science Journal},
year = {2024},
volume = {17},
number = {5},
doi = {10.1002/sam.11710}
}
EUVIMED