arXiv subjects

Ninh Tran

Publications and source records attributed to Ninh Tran.

3 recordsLinked to original sources

arXiv2025

An adaptive procedure for detecting replicated signals with $k$-family-wise error rate control

Partial conjunction (PC) hypothesis testing is widely used to assess the replicability of scientific findings across multiple comparable studies. In high-throughput meta-analyses, testing a large number of PC hypotheses with k-family-wise error rate (k-FWER) control often suffers from low statistical power due to the multiplicity burden. The state-of-the-art AdaFilter-Bon procedure by Wang et al. (2022, Ann. Stat., 50(4), 1890-1909) alleviates this problem by filtering out hypotheses unlikely to be false before applying a rejection rule. However, a side effect of filtering is that it renders the rejection rule more stringent than necessary, leading to conservative k-FWER control. In this paper, we mitigate this conservativeness - and thereby improve the power of AdaFilter-Bon - by incorporating a post-filter null proportion estimate into the procedure. The resulting method, AdaFilter-AdaBon, has proven asymptotic k-FWER control under weak dependence and demonstrates empirical finite-sample control with higher power than the original AdaFilter-Bon in simulations.

stat.ME↗

arXiv2025

A covariate-adaptive test for replicability across multiple studies with false discovery rate control

Replicability is a lynchpin for credible discoveries. The partial conjunction (PC) p-value, which combines individual base p-values from multiple similar studies, can gauge whether a feature of interest exhibits replicated signals across studies. However, when a large set of features are examined as in high-throughput experiments, testing for their replicated signals simultaneously can pose a very underpowered problem, due to both the multiplicity burden and inherent limitations of PC $p$-values. This power deficiency is markedly severe when replication is demanded for all studies under consideration, which is nonetheless the most natural and appealing benchmark for scientific generalizability a practitioner may request. We propose ParFilter, a general framework that marries the ideas of filtering and covariate-adaptiveness to power up large-scale testing for replicated signals as described above. It reduces the multiplicity burden by partitioning studies into smaller groups and borrowing the cross-group information to filter out unpromising features. Moreover, harnessing side information offered by auxiliary covariates whenever they are available, it can train informative hypothesis weights to encourage rejections of features more likely to exhibit replicated signals. We prove its finite-sample control on the false discovery rate, under both independence and arbitrary dependence among the base $p$-values across features. In simulations as well as a real case study on autoimmunity based on RNA-Seq data obtained from thymic cells, the ParFilter has demonstrated competitive performance against other existing methods for such replicability analyses.

stat.ME↗

arXiv2022

Adaptive procedures for directional false discovery rate control

In multiple hypothesis testing, it is well known that adaptive procedures can enhance power via incorporating information about the number of true nulls present. Under independence, we establish that two adaptive false discovery rate (FDR) methods, upon augmenting sign declarations, also offer directional false discovery rate (FDR$_\text{dir}$) control in the strong sense. Such FDR$_\text{dir}$ controlling properties are appealing because adaptive procedures have the greatest potential to reap substantial gain in power when the underlying parameter configurations contain little to no true nulls, which are precisely settings where the FDR$_\text{dir}$ is an arguably more meaningful error rate to be controlled than the FDR.

stat.ME↗