@article{8754a296e69e41c3a6faef1d50b99b17,
title = "A flexible and nearly optimal sequential testing approach to randomized testing: QUICK-STOP",
abstract = "In the analysis of current life science datasets, we often encounter scenarios in which the application of asymptotic theory to hypothesis testing can be problematic. Besides improved asymptotic results, permutation/simulation-based tests are a general approach to address this issue. However, these randomized tests can impose a massive computational burden, for example, in scenarios in which large numbers of statistical tests are computed, and the specified significance level is very small. Stopping rules aim to assess significance with the smallest possible number of draws while controlling the probabilities of errors due to statistical uncertainty. In this communication, we derive a general stopping rule, QUICK-STOP, based on the sequential testing theory that is easy to implement, controls the error probabilities rigorously, and is nearly optimal in terms of expected draws. In a simulation study, we show that our approach outperforms current stopping approaches for general randomized tests by factor 10 and does not impose an additional computational burden. We illustrate our approach by applying our stopping rule to a single-variant analysis of a whole-genome sequencing study for lung function.",
keywords = "association p-value, next-generation sequencing, permutation, randomized test, sequential testing",
author = "Julian Hecker and Ingo Ruczinski and Cho, {Michael H.} and Silverman, {Edwin K.} and Brent Coull and Christoph Lange",
note = "Funding Information: This study was supported by Cure Alzheimer{\textquoteright}s Fund; the National Human Genome Research Institute [R01HG008976]; and the National Heart, Lung, and Blood Institute [U01HL089856, U01HL089897, P01HL120839, P01HL132825]. Whole genome sequencing (WGS) for the Trans-Omics in Precision Medicine (TOPMed) program was supported by the National Heart, Lung and Blood Institute (NHLBI). WGS for “NHLBI TOPMed: Genetic Epidemiology of COPD” (phs000951) was performed at the Broad Institute of MIT and Harvard (HHSN268201500014C), and at the University of Washington Northwest Genomics Center (3R01HL089856-08S1). Centralized read mapping and genotype calling, along with variant quality metrics and filtering were provided by the TOPMed Informatics Research Center (3R01HL-117626-02S1; contract HHSN268201800002I). Phenotype harmonization, data management, sample-identity QC, and general study coordination were provided by the TOPMed Data Coordinating Center (3R01HL-120393-02S1; contract HHSN268201800001I). We gratefully acknowledge the studies and participants who provided biological samples and data for TOPMed. The COPDGene project described was supported by Award Number U01 HL089897 and Award Number U01 HL089856 from the National Heart, Lung, and Blood Institute. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Heart, Lung, and Blood Institute or the National Institutes of Health. The COPDGene project is also supported by the COPD Foundation through contributions made to an Industry Advisory Board comprised of AstraZeneca, Boehringer Ingelheim, GlaxoSmithKline, Novartis, Pfizer, Siemens and Sunovion. A full listing of COPDGene investigators can be found in Supporting Information Material C. The TOPMed Banner Authorship List is provided in Supporting Information Material C. Funding Information: This study was supported by Cure Alzheimer's Fund; the National Human Genome Research Institute [R01HG008976]; and the National Heart, Lung, and Blood Institute [U01HL089856, U01HL089897, P01HL120839, P01HL132825]. Publisher Copyright: {\textcopyright} 2019 Wiley Periodicals, Inc.",
year = "2020",
month = mar,
day = "1",
doi = "10.1002/gepi.22268",
language = "English (US)",
volume = "44",
pages = "139--147",
journal = "Genetic epidemiology",
issn = "0741-0395",
publisher = "Wiley-Liss Inc.",
number = "2",
}