English

Empirical Bayes estimation via data fission

Methodology 2024-10-17 v1

Abstract

We demonstrate how data fission, a method for creating synthetic replicates from single observations, can be applied to empirical Bayes estimation. This extends recent work on empirical Bayes with multiple replicates to the classical single-replicate setting. The key insight is that after data fission, empirical Bayes estimation can be cast as a general regression problem.

Keywords

Cite

@article{arxiv.2410.12117,
  title  = {Empirical Bayes estimation via data fission},
  author = {Nikolaos Ignatiadis and Dennis L. Sun},
  journal= {arXiv preprint arXiv:2410.12117},
  year   = {2024}
}

Comments

This note was prepared as a comment on "Data Fission: Splitting a Single Data Point," by James Leiner, Boyan Duan, Larry Wasserman, and Aaditya Ramdas, a discussion paper in the Journal of the American Statistical Association

R2 v1 2026-06-28T19:23:27.259Z