Sequential resetting procedures and false discovery rate
Abstract
Data arrive sequentially, each associated with a null hypothesis. We develop testing procedures to locate intervals in which some null hypotheses fail, with false discovery rate (FDR) control. The new procedures are called sequential resetting procedures, and they are based on e-values and test supermartingales. We also develop a refined version of the procedures by dropping less informative data points before the block minimum of the test supermartingale in each rejection block. These procedures have explicit FDR bounds under two settings: a classic setting of independence and the more general setting of possible dependence across null data and non-null data. These FDR bounds are independent of the testing horizon, and the general one has anytime validity, but it has an extra logarithm factor compared with the standard FDR level. We present simulation studies and data experiments with applications of sequential resetting procedures to LLM watermark detection and financial backtesting.
Related
- False discovery rate control for sparse correlation matrix.
- Controlling the False Discovery Rate via Model-Agnostic Importance Measures
- Admissibility and Complete Classes for False Discovery Rate Control with E-values
- Empirical Bayes prepivoting under group invariance: false discovery rate control and moderated t-tests
- Multiple Testing Of Composite Null Hypotheses With High Dimensional Count Data: A Local False Discovery Rate Approach
BibTeX
@misc{wang2026sequential,
title = {{Sequential resetting procedures and false discovery rate}},
author = {Qiuqi Wang and Ruodu Wang and Zhenyuan Zhang},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.09339},
eprint = {2610.09339},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.09339},
note = {CC BY-NC-SA 4.0},
}
RIS
TY - UNPB
TI - Sequential resetting procedures and false discovery rate
AU - Qiuqi Wang
AU - Ruodu Wang
AU - Zhenyuan Zhang
PY - 2026
DA - 2026/10/13
PB - arXiv
DO - 10.48550/arxiv.2610.09339
UR - https://arxiv.org/abs/2610.09339
AB - Data arrive sequentially, each associated with a null hypothesis. We develop testing procedures to locate intervals in which some null hypotheses fail, with false discovery rate (FDR) control. The new procedures are called sequential resetting procedures, and they are based on e-values and test supermartingales. We also develop a refined version of the procedures by dropping less informative data points before the block minimum of the test supermartingale in each rejection block. These procedures have explicit FDR bounds under two settings: a classic setting of independence and the more general setting of possible dependence across null data and non-null data. These FDR bounds are independent of the testing horizon, and the general one has anytime validity, but it has an extra logarithm factor compared with the standard FDR level. We present simulation studies and data experiments with applications of sequential resetting procedures to LLM watermark detection and financial backtesting.
ER -